{"cells": [{"cell_type": "markdown", "metadata": {}, "source": ["# Les algorithmes, outils de d\u00e9cision automatique.\n", "\n", "L'exemple du trading algorithmique."]}, {"cell_type": "markdown", "metadata": {}, "source": ["## Introduction"]}, {"cell_type": "markdown", "metadata": {"slideshow": {"slide_type": "subslide"}}, "source": ["### Plan"]}, {"cell_type": "code", "execution_count": 1, "metadata": {"slideshow": {"slide_type": "fragment"}}, "outputs": [{"data": {"text/html": ["<div id=\"main\">run previous cell, wait for 2 seconds</div>\n", "<script>\n", "function repeat_indent_string(n){\n", "    var a = \"\" ;\n", "    for ( ; n > 0 ; --n)\n", "        a += \"    \";\n", "    return a;\n", "}\n", "// look up into all sections and builds an automated menu //\n", "var update_menu_string = function(begin, lfirst, llast, sformat, send, keep_item, begin_format, end_format) {\n", "    var anchors = document.getElementsByClassName(\"section\");\n", "    if (anchors.length == 0) {\n", "        anchors = document.getElementsByClassName(\"text_cell_render rendered_html\");\n", "    }\n", "    var i,t;\n", "    var text_menu = begin;\n", "    var text_memo = \"<pre>\\nlength:\" + anchors.length + \"\\n\";\n", "    var ind = \"\";\n", "    var memo_level = 1;\n", "    var href;\n", "    var tags = [];\n", "    var main_item = 0;\n", "    var format_open = 0;\n", "    for (i = 0; i <= llast; i++)\n", "        tags.push(\"h\" + i);\n", "\n", "    for (i = 0; i < anchors.length; i++) {\n", "        text_memo += \"**\" + anchors[i].id + \"--\\n\";\n", "\n", "        var child = null;\n", "        for(t = 0; t < tags.length; t++) {\n", "            var r = anchors[i].getElementsByTagName(tags[t]);\n", "            if (r.length > 0) {\n", "child = r[0];\n", "break;\n", "            }\n", "        }\n", "        if (child == null) {\n", "            text_memo += \"null\\n\";\n", "            continue;\n", "        }\n", "        if (anchors[i].hasAttribute(\"id\")) {\n", "            // when converted in RST\n", "            href = anchors[i].id;\n", "            text_memo += \"#1-\" + href;\n", "            // passer \u00e0 child suivant (le chercher)\n", "        }\n", "        else if (child.hasAttribute(\"id\")) {\n", "            // in a notebook\n", "            href = child.id;\n", "            text_memo += \"#2-\" + href;\n", "        }\n", "        else {\n", "            text_memo += \"#3-\" + \"*\" + \"\\n\";\n", "            continue;\n", "        }\n", "        var title = child.textContent;\n", "        var level = parseInt(child.tagName.substring(1,2));\n", "\n", "        text_memo += \"--\" + level + \"?\" + lfirst + \"--\" + title + \"\\n\";\n", "\n", "        if ((level < lfirst) || (level > llast)) {\n", "            continue ;\n", "        }\n", "        if (title.endsWith('\u00b6')) {\n", "            title = title.substring(0,title.length-1).replace(\"<\", \"&lt;\")\n", "         .replace(\">\", \"&gt;\").replace(\"&\", \"&amp;\");\n", "        }\n", "        if (title.length == 0) {\n", "            continue;\n", "        }\n", "\n", "        while (level < memo_level) {\n", "            text_menu += end_format + \"</ul>\\n\";\n", "            format_open -= 1;\n", "            memo_level -= 1;\n", "        }\n", "        if (level == lfirst) {\n", "            main_item += 1;\n", "        }\n", "        if (keep_item != -1 && main_item != keep_item + 1) {\n", "            // alert(main_item + \" - \" + level + \" - \" + keep_item);\n", "            continue;\n", "        }\n", "        while (level > memo_level) {\n", "            text_menu += \"<ul>\\n\";\n", "            memo_level += 1;\n", "        }\n", "        text_menu += repeat_indent_string(level-2);\n", "        text_menu += begin_format + sformat.replace(\"__HREF__\", href).replace(\"__TITLE__\", title);\n", "        format_open += 1;\n", "    }\n", "    while (1 < memo_level) {\n", "        text_menu += end_format + \"</ul>\\n\";\n", "        memo_level -= 1;\n", "        format_open -= 1;\n", "    }\n", "    text_menu += send;\n", "    //text_menu += \"\\n\" + text_memo;\n", "\n", "    while (format_open > 0) {\n", "        text_menu += end_format;\n", "        format_open -= 1;\n", "    }\n", "    return text_menu;\n", "};\n", "var update_menu = function() {\n", "    var sbegin = \"\";\n", "    var sformat = '<a href=\"#__HREF__\">__TITLE__</a>';\n", "    var send = \"\";\n", "    var begin_format = '<li>';\n", "    var end_format = '</li>';\n", "    var keep_item = -1;\n", "    var text_menu = update_menu_string(sbegin, 2, 2, sformat, send, keep_item,\n", "       begin_format, end_format);\n", "    var menu = document.getElementById(\"main\");\n", "    menu.innerHTML=text_menu;\n", "};\n", "window.setTimeout(update_menu,2000);\n", "            </script>"], "text/plain": ["<IPython.core.display.HTML object>"]}, "execution_count": 2, "metadata": {}, "output_type": "execute_result"}], "source": ["from jyquickhelper import add_notebook_menu\n", "add_notebook_menu(last_level=2, menu_id=\"main\")"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### A propos de moi\n", "\n", "* Senior Data Scientist chez Microsoft\n", "* Professeur \u00e0 l'ENSAE depuis 2000\n", "* Professeur dans la voie data science depuis 2014\n", "* Formation Data Science de l'Institut des Actuaires\n", "* [lesenfantscodaient.fr](http://lesenfantscodaient.fr)\n", "* Passage en finance (hedge funds), travail sur des algorithmes de trading automatiques (2007)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### A qui s'adresse cette pr\u00e9sentation\n", "\n", "* au plus grand nombre"]}, {"cell_type": "markdown", "metadata": {}, "source": ["## Raccourcis d'histoire financi\u00e8re et technique\n", "\n", "* On d\u00e9bute en 1971.\n", "* L'informatique et les math\u00e9matiques.\n", "* Automatisation."]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Bretton Woods 1971 : le d\u00e9but de la technique\n", "\n", "* Source : [Comment j'ai d\u00e9test\u00e9 les maths](http://www.arte.tv/guide/fr/068432-000-A/comment-j-ai-deteste-les-maths)\n", "* Arr\u00eat de la politique du taux de change unique.\n", "* Volont\u00e9 des soci\u00e9t\u00e9s multinationales de s'assurer contre le risque de change.\n", "* D\u00e9but de la mod\u00e9lisation math\u00e9matique."]}, {"cell_type": "markdown", "metadata": {"collapsed": true}, "source": ["### Informatisation\n", "\n", "* 1984 : d\u00e9mat\u00e9rialisation des titres \u00e0 la bourse fran\u00e7aise\n", "* 1986 : CAC (Compagnie de Agents de Changes) devient la *Cotation Assist\u00e9e en Continu*.\n", "* 1988 : les ordres sont tous pass\u00e9s depuis des ordinateurs\n", "* 1997 : les ECN (Electronic Communication  Network) sont con\u00e7us. Il s'agit de centres informatiques qui mettent en relation les professionnels et les brokers pour effectuer des transactions informatis\u00e9es.\n", "* 1997-2002 : premiers algorithmes de trading\n", "* 2003 : d\u00e9but du trading haute fr\u00e9quence\n", "* 2010 : [Flash Crash](https://fr.wikipedia.org/wiki/Flash_Crash_de_2010), probablement d\u00fb au trading haute fr\u00e9quence"]}, {"cell_type": "markdown", "metadata": {"collapsed": true}, "source": ["### La finance est num\u00e9ris\u00e9e\n", "\n", "* Un des premiers domaines \u00e9conomique enti\u00e8rement num\u00e9ris\u00e9e.\n", "* Un des plus profitables.\n", "* Capable de recruter les meilleurs talents."]}, {"cell_type": "markdown", "metadata": {"collapsed": true}, "source": ["### Hedge Fund\n", "\n", "* [Renaissance Technologies](https://fr.wikipedia.org/wiki/Renaissance_Technologies)\n", "* [CFM](https://fr.wikipedia.org/wiki/Capital_Fund_Management)\n", "\n", "Ces soci\u00e9t\u00e9s emploient beaucoup de docteurs en math\u00e9matiques et physiques."]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Formation\n", "\n", "* [Master Probabilit\u00e9s et Finance](http://finance.math.upmc.fr/index2.php) surnomm\u00e9 le master El Karoui\n", "\n", "Et tout autour du monde et principalement dans les universit\u00e9s anglo-saxonnes :\n", "\n", "* [MS in Financial Engineering](http://ieor.columbia.edu/ms-financial-engineering)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Automatisation possible\n", "\n", "Tout est pr\u00eat pour l'automatisation\n", "\n", "* Tout est num\u00e9rique.\n", "* Les meilleurs ing\u00e9nieurs.\n", "* Les meilleurs finances. \n", "* Le retour sur investissement est tr\u00e8s rapide."]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Int\u00e9r\u00eat de l'automatisation\n", "\n", "* Traiter plus de donn\u00e9es.\n", "* Traiter autant de donn\u00e9es mais plus vite.\n", "\n", "Pour \u00eatre meilleur que le concurrent. "]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Probl\u00e8me \u00e0 taille humaine\n", "\n", "Combien avez-vous d'amis sur Facebook ? \n", "\n", "[La r\u00e8gle des 150](https://en.wikipedia.org/wiki/The_Tipping_Point)."]}, {"cell_type": "markdown", "metadata": {"slideshow": {"slide_type": "slide"}}, "source": ["## Un cas concret\n", "\n", "* Un exemple d'algorithme de trading algorithmique : trend following.\n", "* Notion de back test\n", "* Trading haute fr\u00e9quence ?\n", "* Machine learning\n", "* Pas un inventaire des strat\u00e9gies existantes."]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Une s\u00e9rie financi\u00e8re"]}, {"cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [{"data": {"text/html": ["<div>\n", "<style scoped>\n", "    .dataframe tbody tr th:only-of-type {\n", "        vertical-align: middle;\n", "    }\n", "\n", "    .dataframe tbody tr th {\n", "        vertical-align: top;\n", "    }\n", "\n", "    .dataframe thead th {\n", "        text-align: right;\n", "    }\n", "</style>\n", "<table border=\"1\" class=\"dataframe\">\n", "  <thead>\n", "    <tr style=\"text-align: right;\">\n", "      <th></th>\n", "      <th>Date</th>\n", "      <th>Open</th>\n", "      <th>High</th>\n", "      <th>Low</th>\n", "      <th>Close</th>\n", "      <th>Adj Close</th>\n", "      <th>Volume</th>\n", "    </tr>\n", "    <tr>\n", "      <th>Date</th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "      <th></th>\n", "    </tr>\n", "  </thead>\n", "  <tbody>\n", "    <tr>\n", "      <th>2018-05-14</th>\n", "      <td>2018-05-14</td>\n", "      <td>97.919998</td>\n", "      <td>98.690002</td>\n", "      <td>97.309998</td>\n", "      <td>98.029999</td>\n", "      <td>97.606934</td>\n", "      <td>19454100</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2018-05-15</th>\n", "      <td>2018-05-15</td>\n", "      <td>97.239998</td>\n", "      <td>97.849998</td>\n", "      <td>96.339996</td>\n", "      <td>97.320000</td>\n", "      <td>96.900002</td>\n", "      <td>24594000</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2018-05-16</th>\n", "      <td>2018-05-16</td>\n", "      <td>97.360001</td>\n", "      <td>97.400002</td>\n", "      <td>96.620003</td>\n", "      <td>97.150002</td>\n", "      <td>97.150002</td>\n", "      <td>17384700</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2018-05-17</th>\n", "      <td>2018-05-17</td>\n", "      <td>96.760002</td>\n", "      <td>97.540001</td>\n", "      <td>95.830002</td>\n", "      <td>96.180000</td>\n", "      <td>96.180000</td>\n", "      <td>17246700</td>\n", "    </tr>\n", "    <tr>\n", "      <th>2018-05-18</th>\n", "      <td>2018-05-18</td>\n", "      <td>96.010002</td>\n", "      <td>96.930000</td>\n", "      <td>96.010002</td>\n", "      <td>96.360001</td>\n", "      <td>96.360001</td>\n", "      <td>17128900</td>\n", "    </tr>\n", "  </tbody>\n", "</table>\n", "</div>"], "text/plain": ["                  Date       Open       High        Low      Close  Adj Close  \\\n", "Date                                                                            \n", "2018-05-14  2018-05-14  97.919998  98.690002  97.309998  98.029999  97.606934   \n", "2018-05-15  2018-05-15  97.239998  97.849998  96.339996  97.320000  96.900002   \n", "2018-05-16  2018-05-16  97.360001  97.400002  96.620003  97.150002  97.150002   \n", "2018-05-17  2018-05-17  96.760002  97.540001  95.830002  96.180000  96.180000   \n", "2018-05-18  2018-05-18  96.010002  96.930000  96.010002  96.360001  96.360001   \n", "\n", "              Volume  \n", "Date                  \n", "2018-05-14  19454100  \n", "2018-05-15  24594000  \n", "2018-05-16  17384700  \n", "2018-05-17  17246700  \n", "2018-05-18  17128900  "]}, "execution_count": 3, "metadata": {}, "output_type": "execute_result"}], "source": ["from pyensae.finance import StockPrices\n", "prices = StockPrices(tick=\"MSFT\", url='yahoo_new')\n", "prices.dataframe.tail()"]}, {"cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": ["%matplotlib inline"]}, {"cell_type": "code", "execution_count": 4, "metadata": {"slideshow": {"slide_type": "fragment"}}, "outputs": [{"data": {"image/png": "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\n", "text/plain": ["<Figure size 1008x288 with 1 Axes>"]}, "metadata": {}, "output_type": "display_data"}], "source": ["prices.plot(figsize=(14,4));"]}, {"cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [{"data": {"image/png": "iVBORw0KGgoAAAANSUhEUgAAA1YAAAECCAYAAAD93EajAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzt3X98VNWd//HXh98RKBaICZBSFARECAEEihYI1QjS1KptFaNgCois0GK7IlS2tPqtri1sa7WuoLViaxeq2NpuWalU+aFdy4+0yMafiEbKQlJF6wYhyo/z/ePeDJOQQJKZuTeT+34+HvPIzL038z5nzuRmztxzzzXnHCIiIiIiItJ0rcIugIiIiIiISLpTx0pERERERCRB6liJiIiIiIgkSB0rERERERGRBKljJSIiIiIikiB1rERERERERBKkjpWIiIiIiEiC1LESERERERFJkDpWIiIiIiIiCWoTdgHCcvrpp7t+/fqFkv3hhx/SsWPHULLDzld2OKJa96hmh52v7HBEte5RzQ47X9nhiGrdw8wuKSl51zmX2aCNnXORvPXv39+FZf369aFlh52v7OjlKzt6+cqOXr6yo5ev7OjlRzUb2OYa2L/QUEAREREREZEEqWMlIiIiIiKSIHWsREREREREEqSOlYiIiIiISILUsRIREREREUmQOlYiIiIiIiIJUsdKREREREQkQepYiYiIiIg0wNrytWEXQZoxdaxERERERBqgvKo87CJIM6aOlYiIiIiISILUsRIREREREUmQOlYiIiIiIiIJUsdKREREREQkQepYiYiIiIiIJEgdKxERERERkQSpYyUiIiIiIpIgdaxEREREREQSpI6ViIiIiIhIgtKuY2Vm88ys1MxeMrOb/GV5ZvZnM9tuZtvMbFTY5RQRERERkehIq46VmQ0GrgdGAUOBQjM7G/gBcJtzLg9Y7D8WEREREREJRJuwC9BI5wB/ds4dBDCzjcDlgAM+4W/TBdgbTvFERERERCSK0q1jVQrcYWbdgEPAZGAbcBPwBzNbincU7vzwiigiIiIiLUX20mwqPqwAoKBrAXabAZDVMYvym8vDLJo0M+acC7sMjWJmM4A5wAHgZbwOVmtgo3PuCTO7EpjlnLuojt+dBcwCyMzMHPHYY48FV/A4Bw4coFOnTqFkh52v7HBEte5RzQ47X9nhiGrdo5oddn6Uskv2lcTuv/CPFxhz+pjY4xE9RgRWDojW695csidMmFDinDuvQRs759L2BtwJ3Ah8wPFOogH/d6rf7d+/vwvL+vXrQ8sOO1/Z0ctXdvTylR29/KhmL1i5ILRs56L7ugedzXeJ3QruKajxOGhRet2bSzawzTWwb5JWk1cAmNkZ/s/ewBXASrxzqsb7m3wO2BlO6aQ5y167NuwiiIhImstemo3dZthtxl/e+UvsfvbS7LCLJimS1TGrUcslutLtHCuAJ/xzrA4Dc5xz75vZ9cCPzawNUIU/3E8kXodyjYMWEZHEVJ9r09DlqZS9di3k5weeGzXx51EVryjGfS2802jWlq8ln/zQ8uXk0q5j5ZwbW8ey54FgB7mKiIiIBCk7GyqOd+A6FBSAeRMpkJUF+gKxxSuvUhs3Z2k3FFBEREQkkipOclTsZOtEJBDqWImIiIikg6yTnNNzsnUiEgh1rERERETSQXk5OHf81rPn8fsaBigSOnWspGXLzvbGn5vB3r3H72dr9iYRERERSR51rKRlq2/Mucaii4iIiEgSqWMlIiIiIiLNVrpci1QdKxEREZEG0sViRYKXLtciTbvrWImIiIiEpTldLFZEmhcdsRIRERERkRPFTQKWvWyZJgE7BR2xEhERERFpgOwOwXYospdmU/Hh8Qm3CroWYLcZ4A0/jT+CmhJxk311eO+9OpfLcTpiJSIiIiLSAJOyJwWaF9+pasw6CYc6ViIiIiIizdDJJkXRhCnNj4YCioiIiIg0Q7WH+mnClOZNR6xEREREROREWfUcFatvecSpYyUiIiIiIicqLwfnvFvPnsfvp8l1pYKmjpWIiIhIEwQ9Q1xtVZryWqRZUcdKREREpAmCniGutvJJ4eaLSE2avEJERETSSvy1fa7KuooJGycAAV3XR0SkHjpiJSIiImkl/vo97x1+r87lIiJBU8dKREREREQkQepYiYiIiIiIJEgdKxERERERaV6ys8HMu+3de/x+M54NUx0rERGRFmBt+dqwiyAikjwV9ZwzWd/yZkAdKxERkRagvEqz4YmIhEkdKxEREREROSldkPrU1LESEREREZGT0gWpT00dKxERERERkQSpYxWC7LU6wVhEREREpCVRxyoEHcp1grGIiIiISEuijpWIpJSO0IqIiEgUtAm7ACLSAmVnx64z0aGgwLugH0BWFuiIrYiISJNkd9DMfEHIXppNxYeNv15WZI9Ytf2//wu7CCItVxpe1E9ERKS5m5StmfmC0JROFUS4Y9Xq8OFgA7OzvW/tzWDv3uP3dU0AEREREZG0p6GAQdE3+CIikkS1h6oUdC3AbvOG3WZ1zKL8Zg27FZE0lpVV9+fkrKzgy9JAaXfEyszmmVmpmb1kZjfFLf+amb3mL/9BmGUUERFJtZMNVWnqMJam0iQ1IpJ05eXgnHfr2fP4/WZ8rnZaHbEys8HA9cAo4GNgrZmtAXKALwK5zrmPzOyMEIspIiISKbqMiIhImnWsgHOAPzvnDgKY2UbgcuA84C7n3EcAzrm/h1dEERERERGJGnPOhV2GBjOzc4DfAmOAQ8AzwDZgrL98ElAF3Oyc21rH788CZgH0O+20EQ+uWRNQyYGSktjdni+8wN4xY46vGzEiuHIABw4coFOnToFmhpbdTF73MF/zUPL1ukevzZUdeHbJvpIaj1/4xwuMOf3439qIHsH9rfV84AH2zpoVWN6Oih0cPuZNQhVf77at2pKblRtYOfR3ruwo5YeZHeY+5uaim0ucc+c16Bedc2l1A2YAfwE2AcuAHwGlwD2A4Q0TfAu/01jfbUi3bi5Qx0eGurcKCmo8Dtr69esDzwwtu5m87mG+5qHk63WPXpsrO/BsvkuNW8E9BTUeB+mt664LNC/edQ+Hl62/c2VHKT/M7DD3McA218B+StpNXuGce8g5N9w5Nw54D9gJ7AF+7dd/C3AM6B5mOUVEREREJDrSrmNVPTGFmfUGrgBWAk8Cn/OX9wfaAe+GVUYREZEWT9dnFBGpId0mrwB4wsy6AYeBOc65983sZ8DPzKwUb7bA6/xDdxJ1aXgNBBERERE5ripNvrBJu46Vc25sHcs+Bq4NoTjS3MVPAVxc7J3lIyIiidP+VUQCUj5pEgPDLkQDpN1QwKT5+GMNWxARERERkaSIbscqXl1DxURERERERBpIHSsREREREZEEqWMlIiIiIiKSIHWsREREREREEqSOlYiIiIiISILUsRIREREREUmQOlYiIiIiIiIJUscKICsr7BKIiLQYa8vXhl0EERGRwEW3Y9WunXeVeOdqXj1eRFoMfcAPR3mV9qkiIhI90e1YiUiLpw/4IiIiEhR1rERERERERBKkjpUESkOzJCqy10brvZ69NBu7zbDbjL2Ve2P3s5dmh120FiurY/3nB59snYiIpEabsAsg0aKhWRIVHSJ27mbFhxWNWi6JK7+55nts4aqFPP21p0MqjYiI6IiViIhICzApe1Jo2VXZ4R2ZzO6go6Ii0jzoiJWItCjZS7NjR0kKuhZgtxngDY2q/Q2/iCRH+aRJDAwpO8wOpYhIPB2xEpEWJdQhadnZYObd9u49fj/Eb/NFREQkGOpYiYgkS0U9nbf6lqeQJooREREJljpWIiItkCaKERERCZY6ViIiIiIiIglSx0pERERERCRB6liJiIiIiIgkSB0rERERERGRBEW2Y3WsbduwiyAiIiIiIi1EZDtWhz/xibCLICIiIiIiLURkO1YiIiIiIiLJoo6ViIiIiIhIgtSxEhERERERSZA6ViIiIiIiIglSx0pERERERCRB6liJiIiIiIgkqE3YBZCWL3tpNhUfVgBQ0LUAu80AyOqYRfnN5WEWTUREREQkKXTESlKuulPV0OUiIiIiIukm7TpWZjbPzErN7CUzu6nWupvNzJlZ97DKJyIiIiIi0ZNWHSszGwxcD4wChgKFZna2v+5TQAGwO7wSioiIiIhIFKXbOVbnAH92zh0EMLONwOXAD4AfAbcAvw2veCIi4Yg/lxF0PqOIiEjQ0uqIFVAKjDOzbmZ2GjAZ+JSZXQr8r3PuxXCLJyISjpOds6jzGUVERFLPnHNhl6FRzGwGMAc4ALwMHALOBy52zn1gZmXAec65d+v43VnALIDMzMwRjz32WGDlpqQkdrfnCy+wd8yY4+tGjAiuHMCBAwfo1KlTYHkl+47X/YV/vMCY04/XfUSP4Ore84EH2DtrVmB58YJ+zUPPD/H9Hur7rZnUG4Kve3P5Ow/zby1yf+fKVpsrO1L5Uc2eMGFCiXPuvIZsm3Ydq3hmdidQASwCDvqLc4C9wCjnXL1jXwYMGOBee+211BeymlnsbllBAX3WrTu+LuA22LBhA/n5+YHlVQ9HAm940rr3jtfdfSe4ur+6cCED77orsLx4Qb/moeeH+H4P9f3WTOoNwde9ufydh/m3Frm/c2WrzZUdqfyoZptZgztW6TYUEDM7w//ZG7gC+Llz7gznXB/nXB9gDzD8ZJ0qiabySZPCLoKIiIiItFDpNnkFwBNm1g04DMxxzr0fdoFERERERCTa0q5j5Zwbe4r1fQIqioiIiIiICJCGQwFFRERERESaG3WsREREREREEqSOlYiIiIiISILUsRIREREREUmQOlaSclkdsxq1XEREREQk3aTdrICSfspvPn5JseIVxbivpe9FqaWBsrKgoqLu5S1ZVOstIiIiOmIlIilQXg7OebeePY/fL2/h1+2Oar1FREREHSsREREREZFEqWMlIiIiIiKSIHWsoiA7G8xit+xly44/zs4Ou3Qi0gJokhoREYk6TV4RBbVOpu/w3nv1rhMRaQpNUiMiIlGnI1Yi0qLoyImIiIiEQUesRKRFaS5HTqo0zFZERCRSdMQqKPVdx0bXt5EWLqodjPJJk8IugoiIiARIR6yCEn8dm+Ji79o2EZTdIZofsqOsfNIkBoZdCBERkTRz+PBh9uzZQ1VVVWxZly5deOWVV0IpT0vP7tChAzk5ObRt27bJz6GOlQRqUra+xRcRERE5lT179tC5c2f69OmDmQFQWVlJ586dQylPS852zrF//3727NnDmWee2eTn0VBAEREREZFmpqqqim7dusU6VZI6Zka3bt1qHB1sCnWsRERagJPNehj0jIga8isikhzqVAUnGa+1hgKKiLQA8bMhQrgzImrIr4iIRJGOWImIiIiIyAnMjKlTp8YeHzlyhMzMTAoLCwGoqKigsLCQoUOHMmjQICZPngxAWVkZGRkZ5OXlxW7Lly+P3W/Xrh1DhgwhLy+PhQsXnpD7/PPPM2rUKAYOHMjAgQN5+OGHg6lwgnTESkRaLA1JExERabqOHTtSWlrKoUOHAFi3bh29evWKrV+8eDEFBQXMmzcPgB07dsTW9e3bl+3bt9d4vhtuuAGAPn36sH79erp3735CZnl5OUVFRTz55JMMHz6cd999l4KCAvr27cvnP//5pNcxmXTESkRaLA1JExERScwll1zCmjVrAFi5ciVXX311bN2+ffvIycmJPc7NzU0477777qO4uJjhw4cD0L17d26//XbuuusuAIqLi5k9ezZjx46lf//+/P73vwfg6NGjzJ8/n5EjR5Kbm8vy5csB2LBhA/n5+Xz5y19m4MCBXHPNNbgUXfZIHSsREREREanTlClTWLVqFVVVVezYsYPRo0fH1s2ZM4cZM2YwYcIE7rjjDvbu3Rtbt2vXrtjQvzlz5jQ476WXXmLEiBE1lg0bNoyXXnop9risrIyNGzeyZs0aZs+eTVVVFQ899BBdunRh69atbN26lQcffJC33noLgL/+9a/cfffdvPzyy7z55pv86U9/aurLcVIaCigiIiIi0tytWEG7116D9u2T83x9+kBx8Sk3y83NpaysjNWrV8fOoao2ceJE3nzzTdauXctTTz3FsGHDKC0tBeoeCtgQzrk6Z+iLX3bllVfSqlUrzj77bM466yxeffVVnn76aXbs2MHq1asB+OCDD9i5cyft2rVj1KhRsSNreXl5lJWV8dnPfrbRZTsVdaxERERERJq74mI+rqykfQgX6b300ktZtGgRGzduZP/+/TXWde3alaKiIoqKiigsLGTTpk0nHHFqjHPPPZdt27Zx6aWXxpZt376dQYMGxR7X7niZGc457r33XiZOnFhj3YYNG2gf1xlt3bo1R44caXL5TkZDAUVEREREpF7Tp09nwYIFDBkypMbyZ599loMHDwJQWVnJrl276N27d6Off8uWLUybNg3whheuWLEidrRr//79LF68mFtuuSW2/eOPP86xY8fYtWsXb775JgMGDGDixIncf//9HD58GIDXX3+dDz/8sEn1bSodsRIRERERkXrl5ORw4403nrC8pKSEuXPn0qZNG44dO8bMmTMZOXIkZWVljXr+3bt3k5GRAUCPHj149NFHuf7666msrMQ5x+zZs/nCF74Q237AgAGMHz+eiooKli1bRocOHZg5cyZlZWUMHz4c5xyZmZk8+eSTCdW7sdSxEhFpgTTVvIiIJOrAgQMnLMvPzyc/Px+A+fPnM3/+/BO26dOnT+xcq7rU7nht3ry5xgQX48aNY+vWrbHHlZWVNba/4IIL+NGPflRjWatWrbjzzju588476y0vwE9+8pN6y5UodaxCUJWtDzwiklqaal5ERNLFkiVLwi5CUqhjFYLySZMYGHYhRERERETSzIoVK8IuQr00eUUUZGU1bZ2IiIiIiDSIOlZRUF4Ozh2/9ex5/H55edilExERERFJe+pYiYiIiIiIJCjtOlZmNs/MSs3sJTO7yV+2xMxeNbMdZvYbMzs97HKKiIiIiEh0pFXHyswGA9cDo4ChQKGZnQ2sAwY753KB14FvhVdKEREREZH0Z2ZMnTo19vjIkSNkZmZSWFgIQEVFBYWFhQwdOpRBgwYxefJkwJtOPSMjg7y8vNht+fLlsfvt2rVjyJAh5OXlsXDhwhqZGzZsiD1/tdmzZ7N69WoAZs6cycsvv3zSchcXF8e2D1K6zQp4DvBn59xBADPbCFzunPtB3DZ/Br4cRuFERERERFqKjh07UlpayqFDhwBYt24dvXr1iq1fvHgxBQUFzJs3D4AdO3bE1vXt25ft27fXeL4bbrgB8K5ztX79erp3797oMv30pz9t9O8EJa2OWAGlwDgz62ZmpwGTgU/V2mY68FTgJRMRERERaWEuueQS1qxZA8DKlSu5+uqrY+v27dtHTk5O7HFubm7Ky5Ofn8+2bdsAeOihh+jfvz/5+flcf/31zJ07N7bdpk2bOP/88znrrLMCO3plzrlAgpLFzGYAc4ADwMvAIefcN/x1i4DzgCtcHRUzs1nALIDMzMwRjz32WGDljnfgwAE6deoUSjZAzwceYO+sWaFkh1n3qGaHna/scES17lHNDjtf2eGIat2jkt2lSxf69etXY9nRo0dp3bp1IPkAPXr0YN26dXz/+99n2bJlXHzxxdx1113cc889PP744/zxj3/kq1/9Krm5ueTn53PttdfSo0cP3n77bUaOHMnZZ58NwOjRo/nhD38Ye97BgwezceNGunXrdkLmc889x9VXX82nP/3p2LK//e1v3HPPPVx22WVMnjyZ733ve/To0YOCggI2bdpE586dKSwsZPDgwfzbv/0bs2fP5uDBg6xYsYLXX3+dq666ihdffPGU9X3jjTf44IMPaiybMGFCiXPuvIa8Xuk2FBDn3EPAQwBmdiewx79/HVAIXFhXp8r/3QeABwAGDBjg8vPzgyjyCTZs2EBY2QBlK1aElh9m3aOaHXa+ssMR1bpHNTvsfGWHI6p1j0r2K6+8QufOnY8vWLGCj157jfbt2ycnoE8fKC4+5WZjxoxhz549/OY3v6GwsJDTTjuNNm3a0LlzZy6//HLGjx/P2rVreeqppxg7diylpaV06tSJvn371hgaGM/M6NSpU836+U477TTGjh3L73//+9iya665hoyMDDp37kzr1q3p2LEjL7/8Mvn5+bEO2JQpU3j99dfp3Lkzbdu25ctf/jJdunRh5MiRvPPOO3Vm1dahQweGDRt2yu3qk3YdKzM7wzn3dzPrDVwBjDGzScACYHz1+VciIiIiIi1GcTEfV1bSvgEdhGS79NJLWbRoERs3bmT//v011nXt2pWioiKKioooLCxk06ZNjBgxIuVlOtWou/gOaFAj9NLtHCuAJ8zsZeA/gTnOufeBnwCdgXVmtt3MloVaQhERERGRFmL69OksWLCAIUOG1Fj+7LPPcvCgd0yjsrKSXbt20bt370Y//5YtW5g2bVqjfmfUqFFs3LiR999/nyNHjvDEE080OjfZ0u6IlXNubB3L+tW1rYiIiIiIJCYnJ4cbb7zxhOUlJSXMnTuXNm3acOzYMWbOnMnIkSMpKytr1PPv3r2bjIyMRv1Or169uPXWWxk9ejQ9e/Zk0KBBdOnSpVHPkWxp17ESEREREZHUO3DgwAnL8vPzY+eZzZ8/n/nz55+wTZ8+fSgtLa33eWt3vDZv3sycOXNOeP5qy5Yti50jtWHDhtjyoqIiZs2axZEjR7j88su5+OKLAVixYsUp65EK6liJiIiIiEholixZ0qTf++53v8sf//hHqqqquPjii7nsssuSXLLGUcdKRERERETSztKlS8MuQg3pOHmFiIiIiIhIs6KOlYiIiIiISILUsRIREREREUmQOlYiIiIiIiIJUsdKREREREROYGZMnTo19vjIkSNkZmZSWFgIQEVFBYWFhQwdOpRBgwYxefJkwJtOPSMjg7y8vNht+fLlsfvt2rVjyJAh5OXlsXDhwhqZGzZsiD1/utGsgCIiIiIicoKOHTtSWlrKoUOHAFi3bh29evWKrV+8eDEFBQXMmzcPgB07dsTW9e3bl+3bt9d4vhtuuAHwrnO1fv16unfvnuoqBEpHrEREREREpE6XXHIJa9asAWDlypVcffXVsXX79u0jJycn9jg3Nzdl5XjmmWcYNmwYQ4YMYfr06Xz00Uds2bKFK664AoDf/va3ZGRk8PHHH1NVVcVZZ52VsrLURx0rERERERGp05QpU1i1ahVVVVXs2LGD0aNHx9bNmTOHGTNmMGHCBO644w727t0bW7dr167Y0L85c+YkVIaqqiqKi4v51a9+xf/8z/9w5MgR7r//foYPH85f//pXAJ577jkGDx7M1q1b2bx5c41yBkVDAUVEREREmrsVK2j32mvQvn1ynq9PHyguPuVmubm5lJWVsXr16tg5VNUmTpzIm2++ydq1a3nqqacYNmwYpaWlQN1DAZtq586dnHnmmfTv3x+A6667jvvuu4+bbrqJfv368corr7Blyxa++c1vsmnTJo4ePcrYsWOTkt0Y6liJiIiIiDR3xcV8XFlJ+86dA4++9NJLWbRoERs3bmT//v011nXt2pWioiKKioooLCxk06ZNjBgxIqn5zrl6140dO5annnqKtm3bctFFF1FcXMzRo0dZunRpUsvQEBoKKCIiIiIi9Zo+fToLFixgyJAhNZY/++yzHDx4EIDKykp27dpF7969G/38W7ZsYdq0afWu79+/P2VlZbzxxhsA/OIXv2D8+PEAjBs3jrvvvpsxY8aQmZnJ/v37efXVVzn33HMbXY5E6YiViIiIiIjUKycnhxtvvPGE5SUlJcydO5c2bdpw7NgxZs6cyciRIykrK2vU8+/evZuMjIzY42eeeabGpBgrVqzg4Ycf5itf+QpHjhxh5MiRzJ49G4DRo0dTUVHBuHHjAG/o4hlnnIGZNaGmiVHHSkRERERETnDgwIETluXn55Ofnw/A/PnzmT9//gnb9OnTJ3auVV1qd7w2b94cm+AiPz8/Nr17tcrKSjp37hybqCJeRkYGH330UezxAw88UG9uqqljJSIiIiIioVmyZEnYRUgKnWMlIiIiIiKSIHWsREREREREEqSOlYiIiIiISILUsRIREREREUmQOlYiIiIiIiIJUsdKREREREROYGZMnTo19vjIkSNkZmZSWFgIQEVFBYWFhQwdOpRBgwYxefJkwJtOPSMjg7y8vNht+fLlsfvt2rVjyJAh5OXlsXDhwhNyt2zZwrhx4xgwYAADBw5k7ty5HDx4kBUrVjB37txgKt8Emm5dRERERERO0LFjR0pLS2PXlVq3bh29evWKrV+8eDEFBQXMmzcPgB07dsTW9e3bl+3bt9d4vhtuuAHwrnO1fv16unfvfkJmRUUFX/nKV1i1ahVjxozBOcejjz5KZWVl0uuXbDpiJSIiIiIidbrkkktYs2YNACtXruTqq6+Ordu3bx85OTmxx7m5uQnn3XfffVx33XWMGTMG8I6aXXbZZWRlZdXY7u233+bCCy8kNzeXCy+8kN27dwPw+OOPM3jwYIYOHcq4ceMAOHr0KPPnz2fkyJHk5uayfPnyhMtZF3WsRERERESkTlOmTGHVqlVUVVWxY8cORo8eHVs3Z84cZsyYwYQJE7jjjjvYu3dvbN2uXbtiQ//mzJnT4LzS0lJGjBhxyu3mzp3LtGnT2LFjB9dccw1f//rXAbj99tv5wx/+wIsvvsjvfvc7AB566CG6dOnC1q1b2bp1Kw8++CBvvfVWg8vUUBoKKCIiIiLSzK3YvoLXKl6jffv2SXm+Pqf3oTiv+JTb5ebmUlZWxurVq2PnUFWbOHEib775JmvXruWpp55i2LBhlJaWAnUPBUymF154gV//+tcATJ06lVtuuQWACy64gOLiYq688kquuOIKAJ5++ml27NjB6tWrAfjggw/YuXMnZ555ZlLLpI6ViIiIiEgzV5xXTGVlJZ07dw48+9JLL2XRokVs3LiR/fv311jXtWtXioqKKCoqorCwkE2bNjXoiFN9zj33XEpKSvjiF7/YqN8zMwCWLVvG5s2bWbNmDXl5eWzfvh3nHPfeey8TJ05scrkaQkMBRURERESe9SMmAAAac0lEQVSkXtOnT2fBggUMGTKkxvJnn32WgwcPAlBZWcmuXbvo3bt3o59/y5YtTJs2DfCG+D3yyCNs3rw5tn7VqlWUl5fX+J3zzz+fVatWAfDLX/6Sz372s4A3BHH06NHcfvvtdO/enb/97W9MnDiR+++/n8OHDwPw+uuv8+GHHza6nKeiI1YiIiIiIlKvnJwcbrzxxhOWl5SUMHfuXNq0acOxY8eYOXMmI0eOpKysrFHPv3v3bjIyMgDIyspi1apV3Hzzzfz973+nVatWjBkzhmuuuabG79xzzz1Mnz6dJUuWkJmZycMPPwzA/Pnz2blzJ845LrzwQoYOHRobzjh8+HCcc2RmZvLkk0827cU4CXWsRERERETkBAcOHDhhWX5+Pvn5+YDXiZk/f/4J2/Tp0yd2rlVdane8Nm/eXGOCizFjxvDcc8/FHldWVnLaaadRXFxMcXFxLOPZZ5894bmrz7uKZ2bceeed3HnnnfWWKRnUsYqgquzssIsgIiIiIgLAkiVLwi5CUugcqwgqnzQp7CKIiIiIiLQo6liJiIiIiDRDzrmwixAZyXit065jZWbzzKzUzF4ys5v8ZV3NbJ2Z7fR/fjLscoqIiIiINFWHDh3Yv3+/OlcBcM6xf/9+OnTokNDzpNU5VmY2GLgeGAV8DKw1szX+smecc3eZ2UJgIbAgvJKKiIiIiDRdTk4Oe/bs4Z133oktq6qqSvjDf1O19OwOHTqQk5OT0HOkVccKOAf4s3PuIICZbQQuB74I5PvbPAJsQB0rEREREUlTbdu25cwzz6yxbMOGDQwbNiyU8kQ1uzEsnQ4vmtk5wG+BMcAh4BlgGzDVOXd63HbvO+dOGA5oZrOAWQCZmZkjHnvssUDKXduBAwfo1KlTKNlh5ys7HFGte1Szw85XdjiiWveoZoedr+xwRLXuYWZPmDChxDl3XoM2ds6l1Q2YAfwF2AQsA34E/KPWNu+f6nn69+/vwrJ+/frQssPOV3b08pUdvXxlRy9f2dHLV3b08qOaDWxzDeynpN3kFc65h5xzw51z44D3gJ1AhZn1APB//j3MMoqIiIiISLSk1VBAADM7wzn3dzPrDTyNNyzwVmC/Oz55RVfn3C2neJ5DwEupL3GdegO7Q8oOO1/Z0ctXdvTylR29fGVHL1/Z0cuPava5zrmMhmyYjh2r54BuwGHgm865Z8ysG/AYx1/0rzjn3jvF87zjnMtMeYGbWXbY+coOR1TrHtXssPOVHY6o1j2q2WHnKzscUa17umSn26yAOOfG1rFsP3BhI5/qH8kpUZOEmR12vrKjl6/s6OUrO3r5yo5evrKjl6/sU0i7c6yS6IOIZoedr+zo5Ss7evnKjl6+sqOXr+zo5Sv7FKLcsXogotlh5ys7evnKjl6+sqOXr+zo5Ss7evnKPoW0O8dKRERERESkuYnyESsREREREZGkaNEdKzOzsMsg4Yha24dd37DzwxJmvaP6mks0215/ayLRkc5/cy26YwW0DivYzD4ZYvZwM2sbUraZ2ZX+FPhh5M83s7NcCGNczayrmbXy7we6Uwijvs0pPywh1zu0/RtEcx8X5f2bnx/VfVz76jvp/IGvscysXdz9wOttZp3CyPf/zs8KKq+O/M+ZWccQcs3MbjCzHkFnx5XhDjM7J6TPcL2q3/OJvN9aZMfKzK4xs/8GfmBm1wec3cXMSoAVQeb62UVm9iIwETgWQn4hsBOYADToQmpJzL7azDYD/wxcFHB2kZltB34EfB+C+xBgZtea2fNmdruZXRFEZq38YjNb7+d/JuDsWWb2/8ws0Peanz3Vr/cSM/tKwNmh7d/8/Eju46K6f/PzI7mPM7MpZvYqcLeZfRMCrff1ZvbvZtY3iLxa2VPN7AW8en8Dgu3Y+vu4bcASM7s9yHwzaw38AfiZmQV6zSS/3iV4+5jDAWdPBF4FzgfanWLzVOQXmdkm4Ebg2oCzrzKzUrz92y8gwfebc65F3AADOgF3A38E8oEvAb8H+gRYjk8AfwLeBMYGlJkB/CtQBpxf+3UJsAwrgPy62iaFbd4VeBz4L2As8APgWn99qwDqfaHf3mOBs4ENwNkBveb5wH8DFwBjgHXAFf661gHkfwbYDowH5vvtcHEqX3u/zdsC/+S/318N8O/MgI7APcB6YBwwC1gNjAggO/T9m1+WQPdxft1D3ceFtH9rFfb+zc+J5D4O+LSffT5wDvASMC2AOrcCrsLrxG8CioAOAb3e7YHvAhuBz+J9wN8EfC6g/A7At+P2r+cCW4HBQeTHvQYb/HpfDrQJILMNcDPwPvCZoOpaK//HwMQ61qV0/+r/P1mO15m9AJgJ/HMQ2X7GyOq/c//xK8DwRJ6zRRyxMrNWznMA+JVz7iLn3Aa8N2k58LdUZsfdb423U1yJ9yb9fqpy47Odc4eAd4CfA5vNLMPMLjazzs5/p6Qy39ca6AK8aGbd/cPJI/zyJb0McW3+HnCfc26yc+454O/AV/3clHyjXaveecB/+tntgT1+GVKiVvYFwGrn3J+ccy8AO4C7AJxzR1OUH39R8bOBXzvnNgL3Ab8FvuPnJ/21N7N2fpsfBv6C92FnOfDVVA/Nisv+EK8zeZlzbhPwO7z9TPuTPkFysg8Aq4Lcv1Xnx91vhfe3HtQ+rrruh/D+rgLbx8XXG6/OpxPc/q2dc+6Yv3/7SZD7t+r8uIdDgd8HuI+Lzz4feCLgfVz1EKDTgNeAl5xzrwA3Af9sZl1TkVvNb9fteB/47sfrYJyTysy47I+AUrz92/PA83id6qyA8quAJ51zE/z9azu8Dub/BpFvZq391+A/gd8AM4AzUp3rnDuCV89HgbfNrJ2ZfcnMeqY6Oy6/P/A3f0TCP5tZgZlZKj9D+tn/BzzonJvonPsT4IAr/XVBHKU8C3jOOfffZpaF9/5P6ELEad+xMrNb8Q4XfwnA3/niDxl4EOgH/NDMpvnLk1bnuOzL/eyjeP98P++c+zFw2Mymm9kFycqsI/vL/qLf4P0jWAtswfsmfYWZzfK3T2pbx+VXD834BPAx3reKT+B903SPmX3f3z5p46PraPMNcRl/BN43s08nK+9k2Xj/6Cea2X/gfav8SeCXZrbY3z4V77fqNn8Z+LqZVX+ofwdobWbfSna2/3zfApab2RR/UQX+IXvn3EG8D9vvmtnX/O2T2ebfAf7DvKGHXZ1zm/0P2/cDOcBFya5vHdlfNbNPOOd+BlT6/4TL8fYxKRn/Xyu7u3Puz+ZJ+f6tVv51ZnaG/6HvkwSzj6vOnm7ecM9VeEftUr6Pq1XvrngdiqD2b/Ftnumc22hmrYLYv9WR3wrYBkwKaB8Xy/YXbSegfZyZ3Wpmo+M+zLUBMvH+r+KcWwe8DtySqmz/vgFvOuf+gXc03ICxlqJzGuOzff/lnHvfvC8vDwO5QGUqsmvn+5n/49+/EK+jcQbePu7m6m1SlN3GOXfUzLLxhtv+GNgHXGlml5lZ52Tl1s72vQC8DTyF98Xh5cAjZrbI3z5V9W5tZl3wvkQYifdZMhNYhDcUNKn1rivfObctbvUTwBEzy012bu1s326gt5k9jnd01ICfJrRvT+RwV5g3vD/2zcB/AFOAF4HPQ+zaXOcBXf374/EO45+e6mzgU8Ct/nb/ChzF+1Y7KcM26sku9NdNwRsqdIb/+CK8f0xdUvy6V+evwDt8frX/uC/et5s9U/m6++uq230ksCaZdW5Avbvjjc2tHgY3EO8q3d0DyH4MeNhf9j3gc/6y9kms+3D/ffQo8AW84XcX+evWA1+vbgPgEuARkjh0BfgG3hCgC/HGP/8Y6BG3/mq8o2VnJbPN68m+u1Z2Nt4H/c4BZMfqDYwmRfu3U+T3xPsS5dv+Nknfx50kuwswGbiX1O7j6sru4P/8Eynav50kOztufUr2b/XkP4o37LUL3pGDe0nRPu4k2a2Bn+IdqUzJPg7ogfdh7h/AzlrrfgV8N+5xX7zhqMn6LHGy7Or/aRfj7VMvrGt9srPjnxdvCOxvgZwUvNdOmo93BKV6HzcAOJCs99tJslv7t9v8x4uBKrwvNE4LoM3HAHdWv97AYLyRCd0CyP5/wNMcH4bXC+8LrKGpbvNa25zp//3nBfF+89e1B27HH+rrl2Ef0KtJWckseJA3vCFYs+IeLwIermfbbH/HnKwP+HVlr/DvV+94n8Ubt7ke+F6K6/1z/34GcR9o8T4E/Zy4f8wpyv+Ff78f3ge8a+J2jr8Cxqe6zYn7UId3JOdy/35Sxuieos27AL/G/7DnL/uPZO2QTvGan+bvMEb5jy8EliS57j2AyXGPH4x7fScAu4COcfl3Jysf75/cz4HP+o/7432Y/36t7X6BN0RqJHBNkupdX/ZdcdsMBX7j3x8CXJLi7B/UsW1S928nyb8LuA3vqPxuUrePqyv7B8Dt/uOMuG2Tuo+rJ3sJ8C28IzUvk7r9W0Pf60nfv50k//vV73e8b7Kz4rZP5j6uruylwL/EtXNK9nF4+9Ap/v2twDfj1g3E69CdF7fspySpo1FfNrXO6/H/7m7C+wJ3ToqzW8dtkwU8498fChQl8f1WX37berZfCQxKZXbce20X3nlm/43Xib+T5H05frLsNtT6wsCv94AAsnvhHS1biL+PxevgXBZAm9d+v28Civ37KX3d/de8Hd6X4yPitn8CmNCUrLQYCljPobidwKNxh0c3Aq724VL/d7+Nd8J7o8eFNyL7mHnnn7yJ943ifzrnzgeuAC4zs+4pzD7iH0495LwxytXney3Ce9O809jsRuYfNu+cgDfw/umMAmab2Q/xjuCVpjDb+cMHjvl1Bu/DzmBo2hjdRrZ5W+fcB8BBvMPHA8zsbrzOyFspzD7s1/eQc26fc26Lv/5avG+4klZ3//n/y7xx378ALgOKzOyLzrn1eMODVpg3K+AUoHNT82uXxXnDayvwxroDvIHXiR1o/jkuvp8D/+6v65BIbgOyzzGz8/xlQ4B2ZvZtvCOHCc8Wd4rsAfH1TnT/1sj8J/COXp4N/BJvyFBC+7hGZD8ODDWzEc4bApqUfVwDsx/DO5+xI96H/c+Q4P6tEdl1vdcT2r81Mn81cK550y/vw5spLaF9XCOyfwWMNLORzrm9ydrH1ea8Ycxr/IffABaZf56Xc+5VvKNFN5rZAjO7H+/L0/2J5p4s2zl3xLzhn9X7/LXArXhfaiVlxraTZB+N+186AuhgZt8Ffoa3n0mKk+Qfjv8cZ2ZtzOwevCPlZanM9tftxdvf/M7fv12H9+Xmp1KdDRxz3jlemFlbM7sXr95vpzrbOfe/eKOOugPf9vdvA/GGJSZFA97v1e+7x4EC/3eSci7pybKdcx/jndt1q3nn7i7F62g2ad+eFh0rvHH1xL3oOOc+dM4djHvRLwHK4xvBzObgfdv0MTDdeSfopSq7wm8gB8x1zv3I3/Z9YJhz7t0UZpe7uBN5zTvfYhvedJ0zXNNP8m1M/sf+43vwOldnAoeAAudcU/4JNbrN4+qZgdfuTdWY7OopUa/HG6N8j//48847KTOV2UerP1iY2efwxmgfA37YhNx68+PK8THeycxZeG18kXlTUH8T7x//ArxhYXObEmxmvWrlVX9oWg7k+B+qj+H9c92K988OM+uHN4zhUbxv9h4KIHuov3403lC8DsA459yvg8r292/bSWz/1pj8t/GGpOY6577lnFvqb9/kfVwCbT7Nf9zkfVwTsvPxOs8PAH1IYP/W1Hr7Et2/NTZ/G96MgN/AmzHrx/62TdrHNaHuQ/zf+xzeEYQm7+NqZ8eVodLv4D2P98XVsrjVP+b4MNgDeMOwD6U623mTlxwzb8rvJXgTKvSr/myR4uzqv6dz8PY37fFmAH2ksdlNzD/m/961eMPRjgJf8T8cpyp7edy6hc65f/PvHwIudc41unOTQL2/iPf/vLreVanO9j2G9+XRP/CG+o53zu1ubHZT8v33e/X77mPgN3V90ZuKbN+38I6U/ZP/+ELnXNO+sHNJOsSX7Bve+Rpn4E17+as61lUPxWjj/3yc49Mlnuv/zKMJ08ImmD0If/x19XZB1tvfZgjeDjjw153jY6IbPRVuEl737v79Ro+9TzB7CP74a/whcQG/5u3xOjtNGp7S0Pw6fu/nwA1xj5t0zgPeeTIl1BpOhj8EAO8b2gXxZcPrwM7w73eliUPBEsi+3r8/mSYOT0kge6Z/fzQJTHudhNe9TX3vjQDqfh5N38cllB2/bdCvuf+4yecWJZA/y79vNGEfl6Q2701Tz3moP7uu/WsW8B7eN/fncvzzRJOmd08gexAw0F/epHOLEqx3D2AY0D8F77eG5H8Kb8r7MwPOPieuzZO9f2tIvXvjTcjUJ4T32+BE6p2E132Iv7zO4aApzB5c/T4nbqh5k1+DRJ8glTe8Q6Br8b4lu6T2C4431r96LOjDeNd+eBTvZMuskLKfDDE74Xqncd2jmh1km8ePve+Odw2lzzcxz/A+SP07x6cvj18fn5WJ923xH4F/wRuK8wfguhCzi9Ot3knMb9K1fFpAm4dZ7yZfP6kF1D2oNo8/P/mneEfGtuB/yI5Y9laa/oVRaPlRfd3DrHfY+WHXvc4yJeuJkn3DG6Y4CO+E6S8CL8Sta4t33ZxH8HqdZ/kvzl+BecpOz3xlN/s2PwtvooQf4+3AbklC9iP4s2755Rhaa3319bGy8b5VugNvaNJiZadnvrLV5s0s+yd4X44N8tdPxRuGOF/Z6ZmvbLV50HWvkZXsJ0zgRfk63ge7L8UtOx3v5N3u/s/ZeN9inYd3kt0n/e3OwDuxs6uy0ydf2WnZ5l3xrh+UaN2v8h/3BZ7BG9e9He88ggfwzmfpg7ez/GSt52jqkMNIZoedr2y1eTpl4+3zmjSdelSzw85Xtto86LqftGypeNJGvjiGd1Lsn4Av4w1FKsb7AHce/jdWwM3Ah3iz7Sk7jfOVnZ5tTmLjruvKrj5X52t4wwoH4M0oOA/vROLT436/Sec3RDk77Hxlq83TLLuNstMrX9lq86Dr3qAypjqggS/U7/Dniwcm4V2E8yq8E/iewZvO+SW8i5f9OO7FTXh++6hmh52vbLU53pDCK/3HneK2G4d3jZyOyk5Jm0ei7lHNDjtf2dHKDjtf2WrzoOt+qlug063Xnjox7loF1dO54pxbizdtdS7erH5/A7Y6587Fu0ZOvpn1cp4Gz28f1eyw85UdfHbY+Y3IfhUYbmYDnHMH4n6lAO+6YFXKbrio1j2q2WHnKzta2WHnKzv47LDzw657UwV9HasaF8+Mq+QbQGczG+I/3oQ3S9k7wGzn3Hf87d8DLnDehcyUnR75yg4+O+z8hmZvBLrgX1DYzKaYWSneFLu3uqZdfy2q2WHnKzv47LDzlR2t7LDzlR18dtj5Yde9SQLpWJnZZ8zsCeA+865q3Npf3sbfpPoCcAVm1sY59xLeCzLMOVdlZq2re661eqPKbqb5ylabNyD7Zbyrm5/nr38b+Cfn3DTn3N+V3fzzla02V3bLzg47X9lq86DrnqiUd6zMLB9vfvlf4w07uhb4pJm1cs4dAXDOvYE3f38/YKH/qx/hTYWIc+6oc96ASWU3/3xlq80bmf22v/4F59xzyk6PfGWrzZXdsrPDzle22jzI7GQJ4ohVLt55G7/Eu6BpW+CA8w/pmdn3zOwhvKsl3wOMMrMSvCsiP63stMxXttq8Mdl/UHZa5itbba7slp0ddr6y1eZB1z1xLsmzYQCfAfrHPc7Dq/B3gApgA/AzvJnIzsebsaNf3PadaPq89pHMDjtf2WpzZavNla02V3Z6Z4edr2y1edB1T8UteU/kXWB0DVAJ/As1pzwc5b8wX/IfzwAeJO7KyCQwDWJUs8POV7baXNlqc2WrzZWd3tlh5ytbbR503VN5S+ZQwI54h+G+5t8fW73CObcFyMQf/wg867+o74M3haJLbBrEqGaHna9stbmy1ebKVpsrO72zw85Xtto86LqnTEIdKzObZmbjzewTzpuW+QHgMaAKGG1mPf3t2gP/Ddzo/+qFQFd/O5ryAkU1O+x8ZavNla02V7baXNnpnR12vrLV5kFmB8mcd0it4b9gZkA23jjHY8AuvN7mPOfcu/42FwBXAtucc7/wl52LN2YyGzgMzHXOvaLs5p+vbLW5stXmylabKzu9s8POV7baPOi6h8I1bkxka/9nf+BR/34b4F7g17W2/QbwPbzDdxn+sgzgrMZkRj077Hxlq82VrTZXttpc2emdHXa+stXmQdc9rFtDX5w2wJ3A94HxwBeAR+LWG7APGB+3rBNwN95c8xVAryY2TCSzw85Xttpc2WpzZavNlZ3e2WHnK1ttHnTdw7415AUaD7wI3A9cD2wCJgG7gVFx2/0TsD7u8VXAx3gzeZzRxMaJZHbY+cpWmytbba5stbmy0zs77Hxlq82DrntzuDXkRRoLTI17/O/+C1IMlPjLWuGNg3wM6OMv+yIwLqHCRTQ77Hxlq82VrTZXttpc2emdHXa+stXmQde9Odwa8iKdBrTn+FjJa4B/9e9vB77m3z8PWJnUwkU0O+x8ZavNla02V7baXNnpnR12vrLV5kHXvTncTjndunPuoHPuI+fcUX9RAfCOf/+rwDlm9ntgJfAXiM0CkrCoZoedr2y1ubJTnx12vrLV5spu2dlh5ytbbR5kdrPR0B4Y0Brv8N1TQD9/WT+8GTw+SwpPNItqdtj5ylabK1ttruyWl6/saGWHna9stXnQdQ/z1pgLBB8D2gLvArl+j/PbwDHn3PPOu9hXqkQ1O+x8ZavNla02V3bLy1d2tLLDzle22jzouoenkT3Qz+C9WM8DM4LsAUY1O+x8ZavNld3y85WtNld2y84OO1/ZavOg6x7WrbEvUg7wLaB9CG+OSGaHna9stbmyW36+stXmym7Z2WHnK1ttHpWb+ZUXERERERGRJmrMOVYiIiIiIiJSB3WsREREREREEqSOlYiIiIiISILUsRIREREREUmQOlYiIiIiIiIJUsdKREREREQkQepYiYiIiIiIJEgdKxERERERkQT9fw8RTG4R1Kx7AAAAAElFTkSuQmCC\n", "text/plain": ["<Figure size 1008x288 with 1 Axes>"]}, "metadata": {}, "output_type": "display_data"}], "source": ["prices[-20:].plot(figsize=(14,4), field=\"ohlc\");"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Strat\u00e9gie : trend following\n", "\n", "Le principe : [trend following](https://en.wikipedia.org/wiki/Trend_following)."]}, {"cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [{"data": {"image/png": "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\n", "text/plain": ["<IPython.core.display.Image object>"]}, "execution_count": 7, "metadata": {"image/png": {"width": 800}}, "output_type": "execute_result"}], "source": ["from pyquickhelper.helpgen import NbImage\n", "NbImage(\"images/trend.png\", width=800)"]}, {"cell_type": "markdown", "metadata": {"collapsed": true}, "source": ["### La mise au point\n", "\n", "De nombreux param\u00e8tres :\n", "\n", "* La longueur de la [moyenne mobile](https://fr.wikipedia.org/wiki/Moyenne_glissante).\n", "* La hauteur des [bandes de Bollinger](https://fr.wikipedia.org/wiki/Bandes_de_Bollinger).\n", "* La somme investie.\n", "* ...\n", "\n", "Les strat\u00e9gies ont souvent plus d'une dizaine de param\u00e8tres."]}, {"cell_type": "markdown", "metadata": {"slideshow": {"slide_type": "subslide"}}, "source": ["Deux param\u00e8tres en rouge : longueur de la moyenne mobile et la hauteur des bandes de Bollinger"]}, {"cell_type": "code", "execution_count": 7, "metadata": {"slideshow": {"slide_type": "fragment"}}, "outputs": [{"data": {"image/png": "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\n", "text/plain": ["<IPython.core.display.Image object>"]}, "execution_count": 8, "metadata": {"image/png": {"width": 400}}, "output_type": "execute_result"}], "source": ["NbImage(\"images/trendp.png\", width=400)"]}, {"cell_type": "markdown", "metadata": {"collapsed": true}, "source": ["### Optimisation\n", "\n", "* Choisir les meilleurs param\u00e8tres\n", "* [Backtest](https://en.wikipedia.org/wiki/Backtesting) : simuler la performance de la strat\u00e9gie sur le pass\u00e9"]}, {"cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [{"data": {"image/png": "iVBORw0KGgoAAAANSUhEUgAAAmYAAAFrCAIAAAD0ONKeAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAAFiUAABYlAUlSJPAAAFLxSURBVHhe7Z0LuFVVuff32shFDOVylBBOWxFFJEgjiIgPkEtmugUxCR4KPusQSficNDUNTUEpk8qjUlJ5jn6Qbp7Eg1sQQ0IuUQcQxVRACC9EbkUPKBECbcHvt9c7GU7muux1meu6/794ZuM2x3jnuLz/MeZaexk5cuRIhRBCCFFMDBgw4B//+McLL7zgxSsqfvvb344dN+6ppUuHDx/uJcXjhhtuuHPWrJe3bDnrrLO8pEyJRCJe6CiV3v8LIYQQRcPu3bvbt2/vRaJ06NCB6549eyyaiHnz5g343Oey10shhBCieDni48wzzxw0aJAXibJs2TLOffPnz/fi8XjiiScoc//993vx7PgwhkovJ4ZIJP4BNFG6I3mBbHJBlcdFlcdFlcdFlcelvCvn6nn2IsYMdnCmDBwoOXdyDRw9Azz44IMntG59+eWXe/GwaWQwhBBCiPzTs2fP7du319fXe/GKii1btnDt1auXRWN57733Hq+tvfTSS9u0aeMlhY0kUwghRNExevTog4cOLViwwKJo5/z58/v17duxY0dLieXhhx8+VF8/ceJEL54LvCNxDIkO+6G8JUiEKo+LKo+LKo+LKo9LE6+cq+fZixjs9EJHGTp0aLt27e6///5ly5Zddtllxx133IoVK1zWmWeeaWFHnz59TjvtNC8SBt4HmD4aGQwhhBCiICxcuHDcuHHTpk2rrq7euXPnokWLBg8ebFnomf+dLWzatOnZ55772te+5sVzQ8K/y+zdu/cbb7zhRXx07tw5brojeYFsckGVx0WVx0WVx0WVx6W8K+fq/wPH4qSysuEo7EWKg9i/y9RPGQghhCg8JSGZejErhBBCpIQkUwghhEgJSaYQQgiREpJMIYQQIiUkmUIIIURKSDKFEEKIlJBkCiGEECkhyRRCCCFSQpIphBBCpIQkUwghhEgJSaYQQgiREpJMIYQQIiUkmUIIIURKSDKFEEKIlJBkCiGEECkhyRRCCCFSQpIphBBCpIQkUwghhEgJSaYQQgiREpJMIYQQIiUkmUIIIURKSDKFEEIUI/v27Zs6dWqnTp1at27dv3//pUuXehnxqK+vv+OOO3r06EHhdu3aDho0aPv27V5eeEgyhRBCFCOjRo2qqamZOXPmkiVLunTpUl1dvXLlSi/vWNDLL33pS7/4xS+uuuqqp5566uGHawYPHvz+++972eEROXLkiBcUQgghCkRlZaVfjxYvXnzJyJHz5s4dP368pXCCPPHEE9etW2dRPz/5yU+mT5/+0ksvVVVVeUlhEIlEvNBRdMoUQpQMlZVBFybKldra2lYtW44ZM8aLV1SMHTv2mQ0b6urqvLiPe+65h9xw9TIukkwhhBBFx6ZNm7p169a8eXMvHj1lct28ebNFHTt27PjbG2+cfvrpkyZNateu7fGtWvXv3//JJ5/0skNFkimEEKLo2L17d/v27b1IlA4dOnDds2ePRR27du3i+uMf/3jnzp0LFjy6aPHiNm3aXHxx9bJly6xAiEgyhRBClDD//Oc/uZ500kmLFi0aNmzY8OHDH3/88VNOOXnmzJlWIEQkmUKIEkOfaJYBNTU1I4/FyzgKZ8rAgZJzJ9fA0RNOOeUUrkOGDHFvcY8//viBAwc+++yzFg0RSaYQopSQXpYH48aNqz0WL+MoPXv23L59e319vRevqNiyZQvXXr16WdRx+umnn9C69eHDh734USorwxc4SaYQQoiiY/To0QcPHVqwYIFF0c758+f369u3Y8eOluLgcHnJJZesXLnS6ev+/fvXrFnTr18/i4aI/i5TCFEyuCPmkSMfWkCUDYG/y4Thw4dv3Lhx1qxZVVVVc+bM4SS6bNmywYMHW9bOnTu3bt1qJTmP9u37mT59PnPddddRyY9//ON1a9euWr06S9XU32UKIURRozfPjoULF44bN27atGnV1dUI5KJFi0wvAV30v7Pt1q3bqlWrW7RoMSZKs2bNlv3+9zplCiGaNE3hlMkzNs0zdOwps+DolCmEEEJkiCRTCCGESAlJphBCCJESkkwhRGmg78WIgiPJFEKUGPoLE1EoJJlCCCFESkgyhRCiWNDL5yJHkimEEMWC3jkXOZJMIUTJo8OZyA+STCFEKZHoHCbVFHlAkimEEGWO9hNhIckUQohyRnoZIpJMIYQoTxBL6WW4SDKFEKWHKUGZ6YEUrviRZAohShKpi8g/kkwhhBAiJSSZQogSQ+dLUSgkmUKIEkM/kSMKhSRTCFEm6PTpR72RCySZQgghREpIMoUQ5UCpv63VobAkkGQKIUqGMv4UUx/QlgSSTCGEyDexZ0qdMksCSaYQQuQcKWIG7Nu3b+rUqZ06dWrdunX//v2XLl3qZcRwxRVXVDZr5v930UUXeXmhIskUQogCI0GNy6hRo2pqambOnLlkyZIuXbpUV1evXLnSy4uh08c/vvZ//sf9u+uuu7yMUIkcOXLECwohRBGDrrgP/JzGWIpl+QsUGwHbYqNeKEr2T2EVWp9YStH2jKOystKvR4sXL75k5Mh5c+eOHz/eUnr06HHiiSeuW7fOon44Za5aterVV1/14iERiQS3MjplCiFKm4DelBBxLS9+bcsPtbW1rVq2HDNmjBevqBg7duwzGzbU1dV58UIgyRRClCTJpaX4dTSJhRkbn+jGUpThTZs2devWrXnz5l48esrkunnzZosGeLOurkOHDi1atOjatev111+/f/9+LyNUJJlCiNLDaUCsSJCSseSI4mH37t3t27f3IlFQRK579uyxqJ8+ffr87K67OJg+/fTTHEbvveeeYcOG1dfXe9nhEdFnmUKIkgAhDJyWnDRauhXw62XxnK4CxsdablGwR8jMcnejVZhNVbmmpqZm/vz5XiTKokWL/HrUvXv3Tp06+b/vs3z58hFf+ML8mhr/29q4/OpXv/rWlVf6PwfNDH2WKYQoVTJw/X4pKh4SWRWKthXnI8cybtw4DoV+vIyjcKYMHCg5d3INHD3jQuVc169fb9EQkWQKIUqV4jw/FRWl20U9e/bcvn27/+Xqli1buPbq1cuiBUGSKYQ4hlI5pvhxNpec8X6DLVyK/Z8LRo8effDQoQULFlgU7Zw/f36/vn07duxoKUn4zW9+w7V///4WDZGIPssUQvjBZZfQ0cQExgyOKzZF8iz+Xg3YSbp7CpeVmdmBejKrpFAE/i4Thg8fvnHjxlmzZlVVVc2ZM6e2tnbZsmWDBw+2rJ07d27dupXwjh07vvWtb11++eXdunVDWZcuXfof//Efffv2/eMf/xitJnNiP8uUZAohPPCz5m1LyNX6tcHCAYrkWfy9GrDT3+cuKzOzY2v2QqVArGTu27fvxhtvfPTRR/fu3du7d+/p06dfcMEFljV06NDXX3/dfrvgvffeu+KKK/785z+/WVcXqaxEODmhfu973zv++OOtcMZIMoUQCTHH7b96GUVAIntMJCzLwgGK5Cn89gfsJN3luqzMzI6t2QuVArGSWXD0jVkhRAHAlQe8uRCliCRTCPEREjYhkiDJFELEJyz5zLiewI2Sc1FwJJlCiDyRpeaV1idzhUV9lSMkmUKIxkHtSuiQVwaCoSN1cSLJFEIECfjrgrvv5AY4gQwoZTELZyLbEj1LBhTz45cukkwhRPGSjVrbvQXX+yQ0Kpyi2JBkCiESUsx6kyKSHxEikkwhRFGTpWwXv+rHtbAMNitliSRTCCHKAalsHpBkCiE8ivkdZuq2lc2bWElgESLJFEI0gINO7qPTkqJAVfpAEVLsE/VVMSPJFEJ4xHXW2Zx1GpXhXCP5EeEiyRRCHIPJDFcXiCanhAlkIpmUgBV2AyGyR5IphPiI4lS11K2SKoucIskUQiQ7/YR1MJKYGXH7M6zOoR71c06RZAohUiJj7fQ7cb2ZzANSzdwhyRRCJMScb4ou2OQwiShKL3OEOjZvSDKFEDkh1o/n4vSTpM6SOGyFZaRUMz9IMoVocvjda1qulsJyzdmTgUwm6XaNSD6RZArR1EnF5xbwxFYSh8UCov7JJ5JMIYQoJGFpnrQzD0gyhWgS2FEyxZd4GTvf4vHa5aQfTfbV6759+6ZOndqpU6fWrVv3799/6dKlXkZi9uzZc8opp1Q2azZ37lwvKVQkmUI0LeL6Xx1Qig3/iDTZ0Rk1alRNTc3MmTOXLFnSpUuX6urqlStXenkJ+M53vtO8eXMvkgMkmUKUP7EyWfwHlyZ7tIrFdUWT6pPFixevWLnynnvu+frXvz5kyJAFCxacccYZ3/ve97zseHAMXbhw4Y9+9CMvngMkmUI0XUJxwdI2kQtqa2tbtWw5ZswYL15RMXbs2Gc2bKirq/Pix7J///4rr7zy1ltvPe2007ykHCDJFEI0EO7bP73pzTVlv1PZtGlTt27d/G9Ze/TowXXz5s0WDXDTTTe1a9fuu9/97ocf5nDuSTKFEJkT67gbFcu0fL2kt8mye/fu9u3be5EoHTp04Lpnzx6L+lm/fv3Pf/7z++67z4vnDEmmECIZZSBaenVc3tTX1//bv/3b5MmT+/Xr5yXlDEmmEE2UcIXE1ZZKtXnWsKZwVC25Z6ypqRl5LF7GUThTBg6UnDu5Bo6ecPfdd7/11lvXXnvte1H27dtH4v79+wlbgRCJHDlyxAsKIcoUkyi8aiKtStHhuttd+UDNlk7Y35a/8riJcfFXmA1h1ZMlqT+4g1ussLsX3O2W679aeulSWVnp16NJkyY99NBDe/fudR9nTocZM96sq+vYsaOlGFdcccX/S/BXmHt2727btq0XSZ9I5KOeN+hoSaYQZY75XPOtlhIgRYfrbnflAzVbOmEXcIlGbA2JiL03M8Kqx+F/utSrTf3BHc5ydy+42+MmljQByXzyyScvuvjih37zm3HjxhGtr6/v3bv3SSedtHbtWivg2LZt29tvv+1FKiqeffbZq6+55obvfe9LX/rSZz/72Wz+TFOSKURTxO9e45Kx6w+4dZfoKvSHIXB7EvwVZknAhixxhqVVbeoP7vA3ZCngbrfWXRlLLGkCkgnDhw/fuHHjrFmzqqqq5syZU1tbu2zZssGDB1vWzp07t27daiX9rFq16vyhQx984IEJEyZ4SZkSK5n6LFOIJkc+PWx5ePNE+MUsp5R3NyZi4cKFHDGnTZtWXV2NQC5atMj0EhBXzp0WjiXC/3ID+xSdMoUoc2KPKXEPLqngbsysnsDtSbCSadmWCKoKpR7DGZauhRmXN/sD7frDqddZzMSeMguOTplCiI/Iv6stD+eeT5xABvBrp8gbkkwhRBo4zcuDvy4nfc2gu+I+vmSysEgyhRAiVTJWLNO/LDcB/tulnQVBkilEkyYbJy6vnTqh9JW/kizVV2SGJFOIJkHuPGwuakYbilwSCrJdkEwWHEmmEGVO3KNJAZ1vik0XRJOKk0CPJY+KnCLJFEKIfCBtKwMkmUKIEMhMD3SUFKWFJFOIJooOPUKkiyRTiHJGx7jUKZW+0pgWEEmmEOWPHShzeqwM0Y9LEhz+IcvDIIpGkWQKITLHefDQXXl5aAPyn9MdgBQ0z0gyhRAFoEkdJbN5WIliUSHJFELkm1gZ0MvYtJCOFgpJphAiW7Lx4KUrlo0+da4fTcKZfySZQoimTjbapvNxGRBJgJftQ5IpRD4oP8faBI84UkchyRRCpIcTy3BV0wSpyGWp4C9jRWGRZApR1DRNF1yiR9j8DFYTPN8XD5JMIfJEOYlfll675LoCg5vm3kUEkGQKIfKNU9y40luQU5RTxEalMS3zCvIsIndIMoUQxUJOT3K5qzxuzTl9FlEoJJlClC1F7rWdeXmzs4AdouNmeSDJFCLn6MBR0iQZPglhTtm3b9/UqVM7derUunXr/v37L1261MuI4Wc/+1mfPn3at2/fokULyo8dO3b79u1eXqhIMoUoXkLR2mJ26wXZTOS6V7VDCotRo0bV1NTMnDlzyZIlXbp0qa6uXrlypZd3LH//+98vv/zyhx56aM2aNT/+8Y/Xr18/YMCAXbt2ednhETly5IgXFELkBudDE/lZCsTNshsz1rwsb88pzjbXOY7QDbbu9bcYaMLZkDwXLMtfJnCvhR0uMVCniKWystKvR4sXL75k5Mh5c+eOHz/eUnr06HHiiSeuW7fOoklYtWrV+UOH3nP33RxSvaSkxP2hn7jolCmEKH8CYuaPxuqcKAZqa2tbtWw5ZswYL15RMXbs2Gc2bKirq/PiiWnXrh1XNNiiISLJFCIf6JCRiPz0TNxWci2WrlGNfgZs2rSpW7duzZs39+LRUybXzZs3WzSW+igvv/zyNddcc1pVFRLrZYSHJFOIApPIcYfi0OWsjVQ6U31VVOzevbt9+/ZeJEqHDh247tmzx6KxtGzVin/n9Oz5xhtvPP3004HbQ0GSKUQBkAcPkNOHTbfyXJ8+BdTU1Iw8Fi8jCzY888za//mfeXPnEh40aNCOHTssPUQi+vqPELkGF4zXNkds7ttSopmeg47r1pNkNUo29+aB2N6wFJcYLoHmLBy3XX9Jw1/MlXEF/Le7MPgLuLBIQuDrPwMGDPjHP/7xwgsvePGKit/+9rdjx417aunS4cOHe0kJqKurO+20077xjW/cd999XlJS9PUfIZocfn9dihRWVxptvdEC1v9Sx7Do2bPn9u3b6+vrvXhFxZYtW7j26tXLokk49dRTTz755FycMiWZQhQppS6BKVLYx8xF66imXzglopkxevTog4cOLViwwKJo5/z58/v17duxY0dLSQJa+9Zbu7p37+7FwyOiF7NC5Br8Mn7TfwpJFPbjvHmKPtda8SKJqy0SnHl+OwOPECKBVixsAcOf5aKGs8oF/PgrgdgCIkUCL2Zh+PDhGzdunDVrVlVV1Zw5c2pra5ctWzZ48GDL2rlz59atWwnX1dVNnDjx8ssvRyObNWv2/PPP33nnnUjs2rVruTFaUyPoxawQRYecadGioSlOFi5cOG7cuGnTplVXVyOQixYtMr0ExNW9sz3ppJM6der005/+9IsXXDBi+PC777774osvfvbZZ1PUy7Rg06RTphC5ws4lsccUdzSxXAtYisNfxgJJiC2cqNoiwZmXHzv9/RNo2sIWiE0BEi3qAn7cLUZsAZEisafMvKFTphBChEBAEUUTR5IpRPGiI0vuyEALNRxCkilEbknumuPmkqjDTf6xPs9GF6WpZY8kU4iiIIlGmoLaPy9J5AAJnmgUSaYQOUHylpw865O/udCbltY2HSSZQuSb5GqagdZKnlPBCZu6S2SMJFOI8EnLKefijFISqqDDmSg5JJlCFBFhSV1pqZG0U5QKkkwhyhC9e4yLtFlkiSRTiMLgd9+huPJAJaUiD4W1M3nrtvNIXsZyS6W3RZZIMoXIOfKnxUzc0dExXcRFkilErpDbLTYYEQ2KyAZJphAFIPS3eTrIpkKKvaTOFImQZApRjCTy2qkcklwZuf50UY+J5Egyhcg3OusUCeH2sMarKSDJFCKvJDkmxj0dyhELUTxIMoXIIRkIXn5uEUJkgCRTiHwT+pc2Q6+wKZDiPkPbEeFHkilEvpEXLgm0ERGxSDKFKCTZy6c8e7poyyIyRpIpRMgENEwOWoiyQZIpRAggk6mc9kKXTx0xhcgnkkwhhBDFyL59+6ZOndqpU6fWrVv3799/6dKlXkYMP/rRj4YMGdKhQ4cWLVp07dr1+9///v79+728UIkcOXLECwohMsVOe3aI9J/8Yo+V5MY9a1p63Fx/hYYr47IsxVXiUkQA10XJ+yfQsSIPVFZWBvRo2LBhzz///KxZs1DB2bNnP/7440899RTS6GUfBXXs0qXzV7/6tREjRrRv3/4Pf/jDbbfd1q9fv5UrV3olGiMSCS6xRDBvJJlCZItfpZy3hViHm9xZx831V2i4Mi7LNU3AEpO00pRxXZS8fwIdK/JAQDIXL158yciR8+bOHT9+vKX06NHjxBNPXLdunUX9vPfee23btvUiFRU/+clPrv/e91avWjVw4EAvKSmpS6ZezApRRITloOXoE5FWz6gbC0htbW2rli3HjBnjxSsqxo4d+8yGDXV1dV7ch18voVevXlzjlswSSaYQ4ZPE1ebaC7vjkRAlzaZNm7p169a8eXMvHj1lct28ebNFk7B8+XKuvXv3tmiISDKFKAF03AkX9Wfxs3v37vbt23uRKB06dOC6Z88eiybiueeeu/eee8aNHXv22Wd7SeEhyRSiNIj18vq8TYgAO3bsGDVqVPezz54zZ46XFCqSTCGyJQ/vQpM3Ie0MHfVkrqmpqRl5LF7GUThTBg6UnDu5Bo6efurq6oYPH37CCScsXbq0TZs2XmqoRPSNWSGyJKBYRAlYYiie1yq0gKXEjRohtitEPgl8Y3bSpEkPPfTQ3r173ceZ02HGjDfr6jp27Ggpfnbt2jVkyJBDhw6tWbPm1FNP9VJTQ9+YFaI8kRaKJsLo0aMPHjq0YMECi9bX18+fP79f375x9ZLz6IgRI/bv3798+fJ09TItdMoUIltiD38EQjztWYUu4K/f8LcSYrtC5JPYnzIYPnz4xo0bZ82aVVVVNWfOnNra2mXLlg0ePNiydu7cuXXrVsIHDhwYNGjQn//85/vvv9//lZ9u3boleYvrRz9lIET+CKiXX9i81OxwVbmaCbuAhS0ALteiQpQKsZK5b9++G2+88dFHH927d2/v3r2nT59+wQUXWNbQoUNff/31V199lfCOHTtO79o1UhH5sOKjaU/0gQf+a8KECV48KZJMIfKHky4wJQtXsVyFFnCi6Nr1N+dyLSpEqRArmXlDn2UKUbb45VDSKEQ+kWQKkRXuqFcoYlVTOipEjpBkChECOVUpSaAQRYIkU4iSQdopRGGRZAoRDqZn9g0dS8kpBX8hLEQTRJIpRLYENDLXYpa8fp1EhcgdkkwhQibXouXqlzoKkWckmUIIIURKSDKFEEKIlJBkCiGEECkhyRQiQyorI/raqhBNCkmmEKWHvvgjREGQZArROLGnybjnSymZEOWNJFMIIYRICUmmEAmxo6S7upNl3COmEKLskWQKER/pohAigCRTiPRwUlrATy4l50IUBEmmEMkIiFOsVhVEOPU9IyFC5MMEeNk+JJlChInETIgyRpIpROZIIIVoUkgyhRBCiJSQZAohhBApIckUQgghUkKSKUR89DmlEIVl3759U6dO7dSpU+vWrfv377906VIvI4Ynn3xy/PjxZ599dmWzZl27dvVSc4AkU4j4+P/+0i+fklIh8sOoUaNqampmzpy5ZMmSLl26VFdXr1y50ss7lscff/zFF19EVk+rqvKSckPkyJEjXlAI4SPuTxaQSNSuXlKBKAYbhAiRyspKvx4tXrz4kpEj582dy/HRUnr06HHiiSeuW7fOonEZMmTIX//611dffdWLZ0ckEvw7bJ0yhRBCFB21tbWtWrYcM2aMF6+oGDt27DMbNtTV1XnxQiDJFCIhscc4SymG452OmKK82bRpU7du3Zo3b+7Fo6dMrps3b7ZoQZBkCiGEKDp2797dvn17LxKlQ4cOXPfs2WPRgiDJFEIIkW9qampGHouXUdxIMoWIQ9zv/gghwmLcuHG1x+JlHIUzZeBAybmTa+DomWckmUIIIYqOnj17bt++vb6+3otXVGzZsoVrr169LFoQJJlCCCGKjtGjRx88dGjBggUWRTvnz5/fr2/fjh07WkpB0N9lChEHezGrt7JC5I3A32XC8OHDN27cOGvWrKqqqjlz5tTW1i5btmzw4MGWtXPnzq1bt1rJHTt2bNiwgcD06dPfeeed2bNnE+acevbZZ0fzMyT27zIlmUIE0QeZQuSfWMnct2/fjTfe+Oijj+7du7d3797I4QUXXGBZQ4cOff31191PFsydO/f/XnEFgQj/q6j4sOJDArfc8gOI5meIJFOIxpFkCpF/YiWz4OjXf4Q4BqeOQgjRKJJMIYQQIiUkmULE4cix//USIYQASaZouuitrBAiLSSZQjQg+RRCNIokUwjppRAiJZqQZFZGvIeNVGqjID5CeimESBGJhxDHIAUVQiRCkimaNPparBAidZquZPpfz+pVbZNFZ0ohROpIKoQQQoiUkGQeg46bBUSdL4QocuSkhBBCiJSQZIomSuynmPpcUwiRHEmmEB9hqqmv0Qoh4iLJFE0aqaMQInUkmaKpE1BNiagQIhGSTCGEECIlJJlCHHOy1JeAhBCJkGSK8CkV1dE7WCFEWkgyRWgUv1LqBCmEyIamJZnymKET26U6YgohyhWdMkWZkJZUxxZGQe2fFxdCFJp9+/ZNnTq1U6dOrVu37t+//9KlS72MeKxfv37o0KFt2rTp0KHDhAkTdu3a5WWEiiRT5BzTp5yePmMrb7S5nNojhMieUaNG1dTUzJw5c8mSJV26dKmurl65cqWXdyybNm0aNmwYgf/+7/++7777KDZixIj6+nrLDZHIkSNHvGC5Yy6SY0SkspLThF0ty4X9iaJRXJc6+XFh/3GNFEt3Vy/jWLLpfNeoBYzYhlzrrnw0+RiSWCiEyB2VlZV+PVq8ePElI0fOmzt3/PjxltKjR48TTzxx3bp1FvVz+eWXr1q16pVXXuGUSXTNmjWDBg/++ezZV155pRXIjEjkI39i6JQp8oFfyVyYgD89LpTwQlnTaFuiXAlxFom8UVtb26plyzFjxnjxioqxY8c+s2FDXV2dFz8Kp8knnnjioosuMr2EgQMHnlZV9dhjj1k0RDSTRIb4lc8CflLMDZdUqm20jI6YQhQDmzZt6tatW/Pmzb149JTJdfPmzRZ1vPbaawcPHerVq5cXj0Lhl156yYuEhyRTZEIi4QmkJ4/mgSQtShqFKGZ2797dvn17LxKlQ4cOXPfs2WNRx9tvv821bdu2FjUovGf3bi8SHpJMURjyL5+OAjYthMgbuXghn7BG3EqZ/fMeTOQe/1ds8kAGDemIKURhqampGXksXsZRGo6Jxx4oOXdyDRw94ZRTTuH63nvvWdSgcLt27bxIeESa2jdm4cOKSFP+xiz9ECsYcROT4DqTu2IVK25iIly7cTs/lRFJ3par318srYcVpU5TWNdlQOAbs5MmTXrooYf27t3rPs6cDjNmvFlX17FjR0sx6uvr0dEvf/nLDzzwgJdUUdG1a9ezzjrrd7/7nRfPCH1jViQkdZETQohcM3r06IOHDi1YsMCi6OL8+fP79e0b0EtAU7/0pS898cQT+/bts5Q1a9a8vmNH7Mk1e3TKbMCFm8Ju1PohcMxK9wTmylM4VmsDiVZhbDHDNRe381MZEas5riWGM8BfxrUryp6msK7LgMApE4YPH75x48ZZs2ZVVVXNmTOntrZ22bJlgwcPtqydO3du3brVSr788st9o9x4443vvvvutdde27Zt22effdb/hdsM0ClThE9y7YnNdSkWSKRzWSJFFKLUWbhw4bhx46ZNm1ZdXY1ALlq0yPQSEFf/j/ucffbZy5cvJ8DZ9MorrxwyZAjimqVexqUpnTIjlRwvCeiUyTWgKH7dSkVsYs9qgZTYVvwFCPtvtHDczk9lRFwNrgmwVlyYqxULJIqmQFNY12VA7Cmz4OiUKULAr0yOIleguDYLIURaSDKbKEkkJDYrRb1JSzVzp2GY4SyJNanIpV0IUcxIMpsW6QqVK5/ujYmUKYmY5Y7cybMQokkhyWxyxGpVZooSV/P8ibEFci2T1J/EABfNtRlCiHKlaUmmfKWfRpUytgApOrEJIZosOmWKzElrC+IvnCicN7R5EkJkgCSzqZD96bA4z5c69Qoh8oYkM68U24vNJMYkt1OnNCFEE0SSmT8KKJapNI0KOiHMp6m0lWVz0m8hRH6QZDZFstGYktMnM1iyKoTInqYomZEKec+P4ISHnCRRFP8RMHfCk89zrRBCZIZOmYWheBQCFUxXFHMnnLlAYiwgEv0P9Dd8BpCD/1K/aDo0udnjd/eFdaaFbT2J7JWWIjZKmT2OEKKAaMOlU0gpET0kNIyX/9ooUk0hRCg0OckMSyDDqqckMMkpNuFpUkMghCgGmuiLWbxt8X8JyCSBq/2zxGyIW0mKNedBLzMbEZ0ghRB5o4m+mM2Fn81A2JKUT7eqRGRglWFdlAdByqCJsDpHCCHSoilK5oecZ44SivNNt5Li9/hFeHSj06SUQojCoq//ZEKs707Rm6crRf5qQxeMRo2xAkUon0IIURAkmWkQEK3QNSyWLOUqDxbmgfJ4CiFEGSDJzIpE3rwIvTzqa/+8eJQiOUE2aoa/P4vEZiFEE0SSmR6leOKJVcoApSVCbgiknUKIPCPJDBkceoqyah4/tnAoqpyuGSWElFIIUSiarmT6vzebT+Tx45Jut6gbhRDGtm3bRo4c2a5dW/4ReOWVV7yMeNx9992U6dy5c2WzZldccYWXmjI6ZaZNKKdAP6lXGHrTpQUyKaUUQvjZtWvX4MGDd+zYMW/eb/j32muvDRo0iEQvO4b//M//JPfSSy/14mkiyUyVgFyl67tTVDt/MZpw0bSay+wuIYQoOX7605/u3r27trb24iiLFi165513SPSyY3jhhRfWrl07e/ZsL54mksxsMX0KRZyc1AWEU8oH/k5QhwghjIULFw4cOLCqqsqiBAYMGICCWjR0mrRkOs/b6K+b+jUsEan7cUrmzukHTC0tdcH4wD8bmtJ6CiFEfjhw4MCrr77Ws2dPLx7lnHPO2b79lfr6ei8eKjpl5grcvRc6St5kskT5sCJimwn/Py9PCNH0QPaSQIF33333w4oP27dvb+WNDh06kLhnzx4vHipNXTJLyClLP4QQZUNNTc3IY/EyjrJq1aqWrVol+teq1fFeufzCvv6IFyx3KiOVnFsIRCorOb/YtSE9ekQzQXKJAeIeGf2JTs/iJgLpsZrnCltWoBVrotFKwJ/uryRu4aIlbufb4yR6kEQdIoQfphZXW/UWiCaL4qKystKvR/v379+6dasXicenP/3pAwcOfOxjbaZMufLee+/1UisqpkyZ8stf/urgwQPNmzf3kuJR2azZxAkTHnjgAS8ej0jkGJ8MeJymMnskmUVO3M63x0n0IIk6RAg/TildIJosiouAZKZI9+7dO3fu/PTTT3vxioohQ4a89dZbL7/8shdPQGaS2dRfzEK6PpfygVsarcEvYyJdJIpCiESMHDlyzZo1O3bssCiBP/3pT6NGjbJo6LBJbyobrkSnzIaso4eVJAcdoEzgWGNZAZ/uF0jLilsM/DX7owaJpPjvSl6PlQ8EGrJLhESdn+QpkucKYbjDpQtEk0Vxkdkpc9euXeeee27Hjh1vv/12ojfddNM777zz4osvuu8EtWjRYuLEib/+9a8t+txzz7322msELh8z5vwhQ6ZMmUL4/PPPD3yHyNApM3NSd81pOfHYwpYiJTAK9buGQoiSALH8wx/+UFVVNT4KgdWrV/v174PDhz/44AMvUlFx7733Ipb8i1REVq5cRWDMmK9s3rzZy24MNulNZcOV1inTf0oLhP1i5s/yY+kGuYmKGa5OV8yf4r/LCkCiRFeDpZQW/hFxxE10BPpHiLgwi7jaqrdANFkUF5mdMnOKTpkZ4vxyxg46rRuzb04IIUToSDKTwSHGneHSIgOpy6whP9nXIIQQIgmSzKxIRRpTUTJXRsfKtFB3CSHyiSQzSLpnNXltIYRoIkgyPVBK/sX9ffYiFMUkui4JF0KIHCHJbMD9ILhF/YJUVAokORRCiAIiySwHJKVCCJEHJJlCCCFESkgy80GIp0Cq8teW7peVhBBCZIwks1SRWAohRJ6RZCYjz58R6iNJIYQoZiSZRUFYYinRFUKI3CHJjE9JaI/ezQohRD6RZCYkFNXMqfTqTCmEEPlEklmqOL2MDQghhMgFksxjCPwMUH7IrLnAW1nppRBC5BpJZg7JtYzps0whhMgnksyco/OfEEKUB5LMXCGlFEKIMkOSWSykJbHSYyGEyD+STCGEECIlJJlCCCFESkgyhRBCiJSIHDlyxAseS+/evd944w0v4qNz585x0x3JC2STC9ncfuTI4crKZgTe37+/9Qkn2NWyLMztf9m2zSUGKKDlcXPffbevBdq1eyb0yv3krXL/iBjkZjwikI1tqjwuJVo5U6vV8a1Y/gSIxp1RxWk5hFI51xdeeMFLKlYqKysT6VFytm3bdt11161evYrwoEGDf/azn51xxhmWFaCuru6nP/3p8uXLX3nllcOHD/fo0WPy5Mnf/OY3vewYIpGYP+TDxLhEIvEPoInSHckLZJMLWd3eSN3Fa3ncXBLtn4UtMS7Z5IIqj4sqj0vRVt4oRWt5KJVz9Tx7EYOdXigd3nzzzY4dO3LGezzKJz/5yU6dOpHoZR8LBU477bRbb731qaeeevrpp7/xjW/QNTfffLOXHcOHMUgyP6JoLU+U69JzUblDlcdFlcelaCtvlKK1PJTKuXqevYjBTi+UDtdee+1xxx332muvWZQAURItGmDv3r1e6CgXXnjhCSeccOjQIS9+LJ5O+ojT128eOvS1LVs+rIj/ZwyJ0h3JC2STC1nd/mEjv5VTtJYnyv3wQ+8lRi4qd6jyuKjyuBRt5YiGF0hA0VoeSuVcceyWUmYsXLhw4MCBVVVVFiUwYMCA2tpaiwZo06aNFzrKpz71qf3vv79nzx4v3hhByaRbq9aufejtt724EEKI0gfHXn6qeeDAgVdffa1nz55ePMo555yzffsr9fX1Xjwpy5cv7/Txj3fs2NGLN0ZQMq9/9dUPvKAQQogyAceOe/ciJQKylwQKvPvuuxyg27dvb+WNDh06kJjKwfEXv/jFMxs23HLLLV5cCCGEKBW8jxCjrFixouF1eoJ/9uns3/72N8KB7+9MmzaNxETfAHI8+eSTLVu0mDhxohePh/cBpo+Ef2QihBBCFIr9+/dv3brVi8Tj05/+9IEDBz72sTZTplx57733eqkVFVOmTPnlL3918OCB5s2be0kxrF69+otf/OJFF130yCOPeEnxiP0jE0mmEEKIUqV79+6dO3d++umnvXhFxZAhQ956662XX37Zi8ewZs2aCy+8cNCgQY899lgSWYVYyUz27WQhhBCimBk5ciQSuGPHDosS+NOf/jRq1CiLxvLcc89VV1/ct2/fRvUyLjplCiFEI+zfv/+EBL9CVUDq6+szcPplxq5du84999yOHTvefvvtRG+66aZ33nnnxRdfdN8JahH9wPLXv/414W3btn3uc59r1arV3Llz/X9wct5558XtyWI5ZS5duvTyyy8fOHAgdh84cMBLLTRPPvnk+PHjR48ezTbESyoCfvazn33iE5+4+uqr7RtiRUIRWrV48eLq6mom1SuvvOIlFRpMuvTSSzt06NC5c+dNmzZ5qQUFM5jknTp1wl+w+rzUQrNixQrWXdeuXa+//vqimlGcYOirymbNCBSJYWYVMwqrpkyZ4qUWFDwnlsyePbsgXYRY/uEPf6iqqmJiA4HVq1f7v0P7weHDH3zg/SHI2rVr333vvbfe2jXiC1/o/7nP2b/PfW5AXV2dFWichm8F5ZEbbrihYbMWiXBt27YtgREjRnh5hWPcuHHHHXecWcUGpGWLFvbjEYl+EiI/WOv4EYbprLPO2rNnj6UXlmKz6q677mrXrl10LlcwcHiTv/3tb15e4bAf4sIkZlTv3r3nzJlT2LlkvPbaa2eeeSYm9e3b97LLLnv00Ue9jAJhfWKrD6uYTtOmTSuG4bPpbcOHVQQuvPBCL69AMHZdunRxVlmYaeZlFwi2OA2eM7r0CHzmM59p9HuqpYX3NVkfOTxlcl7+7ne/26dPH7qVsCX+y7/8Cxr54gsv7Nu376WXXjrv3HPZYL733nuWmwfYTXA2Gj58uH+Lfcopp+BqX3v1Vax68MEHj2/dmquXl3vMpM9//vMc3dw2jUDz5s1/+MMfcgr/5Cc/ueP11//3f//XsvJDcVq1ffv26dOn19TUePGKivXr17/33t4JEyYwvw8cPLhw4cJTTz3Vy8sLcec5u9pWLVuy72ZGPf/889/85jfz+QIt1iQbwS9/+csMKyatW7fukUce4QQcLZ4nOP2zY77lllucSfQJUSz5wQ9+gFUvv/zybbfdVsDhc0eNq666Cg+ASXDfffehB3m2yr/69kd/Sp6t/OTJk+fNm7d3716suv3225EoNkBWPg/ELr2lS5f+/Oc/Z3vBvvnv+/adf/75zz773EMPPeRllyumpaHz4osvdurUiUHl1MyEQyntOMLV/yt/AwYMINeL5B621WzQaJEDLrax17Z0dkbMQgsDp5bu3bt7kRyzevVqM4Yu4nraaad5GVGGDh163nnnsU4YqXyeCYrQKrSZRmkRe3AfhC0dM0466UROJxTAj+DpLD0/xM5zzCAdGWCmcZK7+eabBw0a9O1vfztvp8xES2/t2rVt2rRBGO6//362O3DPPffYLXmAoyTHbhs7TGKCkUif9OvXjwMT4WuuueaCCy7Ip0mQqK8MGzLbPT/xxBOWmAeSrz6zinmFVfk50iVaenfddReJM2bMsCjziijTzKLlgXe09BGCZNJTDS+DBwyYP3++l3TkSMMXliIR9teE58yZE4lU9u/f37KAfRO7S2SJMSDXSw0Vtj+4KhbqX/7yF0th4NkQ4TUII5CcSxjgO++803KB1cJEtDJmebjwpAMHDrzwwgvNXwD9gMugE2zq2zL46le/arnYQ78xBTGGdNyupYdLcVrF+ezaa6/FoxE2H/Hv//7vzCj8F9GG154VFaNHjyYdexAnTCIXr4fZjGAuXu6lNc8x0qzCJNyx+RrXw2GRlkmvRn/5BRVnh0EX4YiJskD8m8VQwJMyW/wmEcYk+5txFiZdQZ8QZuwwhnWKbpmUUownyoUSZOCmDJt4nIC9eKiku/ocI0aMYGq53yIPkSRLD9v8Sw8LsZOxW7ZsGXtWhs9e9pQTnk76yFYyp0yZQq/RWQ3v1iORG264gUQ6mpSzzjrLygAbE5bEhg0bLMpEYRtFGWCaVldX29iEAlWxMLCKw6KdKW1JIJlY+K1vfcuKASadeeaZzr2yfkjhLq5w6623WnooMMmso+yR582bRyKmYt6wYcOsDDD/KGDzFVfCUcDSsadPnz5PPfWUZYVFEVrFisUkjGHsqN9OjZiElzc/a9hncjayuA+UAKeDGWPGjGGUcTohzihIa57bRhuF+OEPf7h3716KoRPczh4RkbCS2ZOuSTRNefyd+wCMcSQLhbNo9jAEtlFg00lb5liBrsBCCwPbLMywcxsGEKZnUHSMHzp0KLdfffXVVjIsMnNTFOBKL+VoD53W6nOabVaRCOHuLdJaerbkmVf0DyPIjZjNXbHqXtJ4OukjVcnELaIoTCn/bOYAR2cheITZqzL56DjbLtF9FHbvYNmDkMVuxaIMgw08VyYHg5TZun3yySfxldTg3zninrDqjjvuIMzsp1021JiKMaRfc801pNvOGsfK2NtMBXyKWbVixQqWFlkZODhMYiWwn/WfX+k9mja1ZmOIKrNjsJXJs1sHWtN4fKYdrpYwSwJf8/jjj7MDoBg1cM3MmxSnVThNbnT9D7gAGurduzcDhCUcQRgF81bMKNLdjGIuMbLm+yjgHykMc/MwXUKc5wF3xizNzKpQTLKvszHE5Jqiwz333ENvX3TRRRZNC8YO6eUM5MWjsGqYQswljiOMAhbawsQehtJJEQZgEupI2BzuLbfcYlkMJSXtVaTNvbQIcfho3QzAGBTLUhoKpU8oq88cmrMBkzLuJch+6dFXhDlfsp+woWQNckansK3K8sDTSR/JJJNBpU/pvjPOOINRpAcbXuZEIkTthQATnXQmhJV/5JFHiNoKZFfCoDpH9thjj9Gz9tmhG2ML2NRB5yyxUTCJDSk7IJrAGKyiIWrAjzPYFKAVxnvbtm1WngnHKNp+n5EeOHAgiWYYfoSsuF+OZVtK5fa5VKM8+uijqCz9gMuwjkJXMIkDmflNs8G5KhwNlthqobDtc80Atg5M3AkTJlCYqqgEWEsNu+OKivvvv7/h/tQoTqs2b97M5Dn//PNpi3uplgByYl3NsJLoVvKcOXMYhXHjxhFmlBlxN6Psw0I2PYQDM2rGjBlU4p6rUfIzz9mrYRXu2xKTE65J3G4m0c9UwnbHsqifzk/9WLB8+XKexaYNz0K13E5bttZokcpt/gAlGVxOJIQZbgq7fS0rkamISBDG/1KVO/hSCU9qWSmS0+HD1VCACl1KioS7+khhK+BSuIu+jX2HnJxwl571Ek9BJX/729/MMJog6t4ulAGeTvpI9o3ZSy+99Le//e3vf//7448/fvbsexEkJtCokSN37NjB/pQCW7ZsadmyhftdInq/c+dT//jHPxL+zGc+s3v3HtaSZTHnWrZs+fe//52w++ogAYYBxWJsGEhLjCXwfdqvfe1rTMQlS5Ywik8sXoxVr7zyCvNywYIFTFMKUJ4n5WmtfMPbj+bNbTGcfPLJf/7zn0k0G2j0n/UfMNguxXjhhRcefvjhE1q35hYvKSmXffnLuKHf/e53qMjcuf8Pk9544w16YN3atQ888AAFmFLY8PbR/6TayJEjTzih9eLFiwmffvrpO15/3dKhT58+XN955x3E4Ac/uJkZzCynl7CfdPeNvlQoQqvwGrhI7uJ2tjjUwL3nnHPOqlWr7CcimWys5HfffdfKX3zxxR1POYWdLOFPfepTu3fv5hEsC1/8sY99rOFl+7EzateuXb/61a9Yt7169bLERsnDPGdG/fKXv8TRfOITn7DE5IRrEpWgUoRnzpzJ9bbbbrM1RZ9/8MEHDV/MSQHW0Ve+8pU1a9asX79+6LBhTB6smjx58v/u3n3ddddRAEE9rlkza4gsnprZwkAzxIMHD2aVcWSJ1tTwEo8JRhnCV1xxBd2ydOlS+07vxo0bX9+xg/LRgvFx3982cjp8rB36igOiS0mRcFff4cOH33//fcJmA67v4MGDl1xySTQ/JUJfetRAGDVlCtHhZhhOmCjjHi1YpqxevZoe5ChNF5iugm0ZmMpsIgjQIy7xoYceomct/dZbb2X22ynNYCuE/hFA1ajcn0VJ+9smxoyNLYttwIABHAfZatkbPz9PPPEEVTEz2KAxQkwvS2d7xS2zZ89mp0Y9pNjrgquuuor67eU7N3KXvVIAjGcl2L7VvINtisFGnXVFGLm9+uqrr7/+eqxCKcFtxg02s5dddhm5tLJ//34vNQodxZPSP9ZRlnvHHXfwaPaOouHDm0gEpWkoHW33vPPOw2DC9osVLguIxn6nxnT9ggsu8OJHYfjwZV27dh0xYgQbbUt0w1coqxh9CnP6NEvAmcTMYTQ5cGCPJbKMmVE2N+zNmP/FDqcBm1EYQ1sYZulAbSxOKsEfcSMz8yc/+Unv3r15QPeiz0HnMHzMJU57bjr5rSIQ7jxHzmmR89OAAQNoAgIzCl588cXu3buz4Ysdu9BNskqwhygOlHXEMrFjhB/ORkwSOwkZduMnP/lJe4fJeLm3LwwiKwv7CbOCqBNVsHSuTAAswWzkikFhsBruiYII8Yy2eDlFUYxFysGFRFa9PbUfFjuW46AxfsKECXZj7vrKi0QdDgX8s85PoXyCbQXM3QXAc6K+5vHs5TOrg6v1UmDpMWRZLj0qZBZRCS6dAzRPx3z2T55Sxzta+mjY8dEdzHWnMcZf/vIX+v2LX/yiFz86F5l/lGdHSdiO4X6PieqQa7OEOhk2RoWwrQqTRgbMOpdcRsWqcthnG8CoMIcYD1JItzk3Z84cVhS1Rct+hL1tsLAtVP/bQmrAGCYlkMXKNNWkdepn2RDGneFPqQSrmHP+13osP/d2hVymkb3dNVg25Lr3UWAdxUaEkqbrtr+2z0gMpiltme8mQFfb/G5YSMeuFofzqg62HdyLVUxT+pOAe/dVEKsozJBRP4Wxhxroaude6XwqHDJkiEUd9tmzjRe1cZd9kGOwiSHXTKJOarDvHTBtnPE8GkrZ0G4kgldl2dvDOjCMgWNh2xDTM27blLt5DgiDzXOeyHoyAI6G8hhmt1jTuTDJPgkzHnnkkaFDhzLWAQmnBm6kMFPdPiixdu3KULL0Gsr5YAphhvlcJhVK7C+DMdRmH+AxQJTEoRNmLRPu37+/1QzMW6ufjgo4IiuDx2B6o8cIJ1Jh8wFy11dWD5swvEfAR0GhfILVM2XKFBaa30fNmDEDSygGPBGGMfHcl/JysfTow2ipBkHFGJvnqLJbWeWBp5M+KvAvDBVdbJPGwYjiffz7L4Pjl2mYwSwHmwTAnov1byJEVzKKQAHqx33YeINtEnGm1E9tbHXdOmE9gO2MqJbhHzBgAGG7lyVHVYEPhBom37FfhSWKiLrmmL5gRtIWMwOTSCHAJLYyFMYe5hYdggJxaHPrhGmNL7DVjuW4G+rH71gu05pHdlplsM+icv9KZkpRLfVblMXPDDO9YX9Hbtu2bWmFp7NPWfzE7Sj8HXfZZx6AzyU6adIki+bBKkYBq+gu57/oE1wbN9JL1ImT4kbnrLGcPrdPrdzQADLGTHMptMjidDPKvutovW2f9zB2nBKYhxQzrwfYzFEGSyjDA1p5V6ft323zi8E8Fw7asnI6z5nGcWeUgbU0wQhyLxWSYjfm1CSDuxgXPDthl4W/69OnDwNNPYFhIsC0p8P9iUCjdKyzgTJEnSu3IxrqRZiHwh5qxhisYl3bgvIT21fWlp2MA3sOy8pDXzFMTGk6xwywvXthfQLT/pprrmHH7ESRcycWIuTmOTkC0sMEXC/lbulBoMfKCU8nfTR8/YcBZmbHvstiEgRGHZfNQK5YsYKwjQ1CRVd+4QtfiOY3dDpj43qQEWUgmYVs1iyRHd/s2bMJMDBMF+6lvK2lwJIAM4zR8uKWEvPfDqUextIct01oVgsVsvwI2+4JV95QNAqbAzwmE5RNFlaxLcI80gkjzxRmQjB3CThTTaTtEWyT5XbozHiiNtEdtim2CW0m0UV0nX3VAgnEPP+S5rmGDRvGRGefG9tRlPR3lHkTpjJryVwtMFL0jHkByJFVbok2HI+if5lOhfTVsmXLSGRcMNsKAAsYGyzLoPycY/8MlyEg0d6Nm0kNnz37vlyNy2BSOVXGwWEhjTKpbMIwNDZ8t99+O+lYRaPMOlLMZsYXv+Cei0RGnyYsCqHPc2cS4cCMstObPSlhDKYwVw5hDRUdJXSTLIV2mbcUs17CNtLdLYwdYeYM08D/EtXo2rUre2tXGHDEGGB/imfpjA4pTDOLonxE3YNQM9OVfmDpuQ26v684d1Kehvx9xaRi7AAB5sp8oCvcfIBc9BVdYa0zD+kN+gqQMVKsAAbk2SdwI2VIRyxZ+DwOtYGtHT/YxgPSjV48CuVDX3oBMNJ6o5zwdNKH941ZBpgzgf+B6SmGk9EibOlMWVLYZUTzP4KBp6OZ5eTSoThKLyMe9vKBgH2B0OY6mzVuZBJHi3yE+VyTAbOBHSvuz59y5513UmHg01BMpTbScVVcEdQkrwvYfLHqCNgnBFYVNXAXVkWLeFiL9gi2YIB1QjHmE2ErwENRgD1aNN+D/rR3U0xEOoq5GDvtbL/pb4VAko5ir0BVTHSmMoUZGrdjfSz6PclQrAKrwdYqAaoigGMi/OCDD7LU6auGckfBzeFfGCn21HavXWnIzSgjcBoA7uW5GBEcKCcwKve7qljc8OHvWMwcnnhwnLLlGrTr/DiwO6RLzWuzI+HBw53nKc4oJqe1Qjq4z+dysfRsmdC3lGGsJ06cyOjErjiDLMpQ2KJmA/XbRgTMw3JGoWk35QxEkWenZpuT/j+WiEuSvmLoo0Uamub4i1X0GDJv9Zv25GL4wK0+9APdwiqi7vH9WKO58wmGGz6ejgCTmUTcIH3CjVbGD11kSuzgrtCXXlPA00kfFdYdnOIZNuYfYUvBFTJrbQZbynnnnUcKAcAju99JIpfJMXDgwMmTJ78c/XtbzuxXX301k5spwi6PAlYD16FDh9o4MVfs1YGB/2Wo/FoIzHsmhLk2S2QeYKc7yjDGmGQ7YgqgKDZNgR0ZrdMWG0yei9mJx+cR2BTbxpNlb3WyaFlIBEaOHMnEarg5in0I7/9MFKiKMqwQwnY7swob3DsZEtnf4U0syuKxwyLgE+lPvDkdZauLK2vyjDPOoE5EiLasTq7JO8q91KKLuJE+sbWHT2FRkc4JO2Or2F5gFYuHBUmAe4F0xhRHQICS2GB+E0zU3TABBlOAJcfwMTFsXlEAk/yLkG6kjO2dSTHLgcGiXQaFx2GakWUdRZQKObuQEjt8FgVaoUOoxCXSCs/uNIDZS1+x1SBsn45nMM8DJlkBqyGVGYVzpDPtkekHwtRmxxQKZGYSKYwdPUxVFo1a1FCD/c0AAfqN0yEBZheN2tA4rDD6RJZ/3QEGIB4EbPmweeXRbCdHGY50VpIrJjHZ6Jlrr73WBJWxYEIyV8l1kA7J+8qOeg3TKfoVBLuLeUhJe7+S8fCRwnzAQsqzpgg32HT0EdzqcxsCRpmUwP7ACNEn4Dl55MA7T2BK2PCxL6QrbG4DXpqovfp2MBb4BOYAYe7lSovYk9nSs3QHKYYXL3c8nfTR8N+BI2PIkCGMur1Ds+5gkFg2btdjQ8U+iN4kAPhTy/JDj9tbL8BtcWUv41wVsD00/8IQEra5C/aa0faGbkg4NDCubvfN1b4Z66KUxxKmsi0qsP1XACYEz8KNzAMegbBpg4HiojcEWDz+jR7CzDpxf/xkLVKY2+2JLIUZT81OP7AQM3g011Hu40Y/bA4s16xiRRH2V5tKR+HU6B8rBjfffDNR64HbbrstXatoncFiZZLLvdal5sQNGuIuzKMTKOmW2Yboq+/zzz/fooDjxrGyIDlk0If2SQzejTrNyYIdVRFmytCltEVJy/JDJfSAmURH4WH9YwcYw8D5u87GyBqyycMMoWfcyBLAEht0PBSF05rn+M1GTUoyo+xjVMow6Lg8++aatWV30VHpmsSDYwbPSC61EaAht6+Cb3/729js9prAFKIMbRG2fnMBdplk2fc7LAWVxVrbZAAnPJrASHTOxg7s2BfADHNl7GWpn+R9hXgTpgz3MqVdFj1gnZDB8BkYxtjRVywKngXcEgMSAy9IbO24hgzLsvmWpU9gIChguTyFl3oUGz68K2cGarZVSVtA0ywia9eu7E4o499GMM0yWHoCPJ300fBOnC5jJD744IOXXnqJsP2FDYPKkH/2s58lDKgpJVu2bMmGyLr+7bffvu+++9BafLT9WRW89dZbjOt3vvOdf/7zn2+88QabOFzn9OnTqYHauB48eJAUAieffDLe0P3NZc+ePTt0aL9u3TqLYsOBAwco2axZM7wzNZtVlZWV2GAFuK5atQqraLRfv8+aVQ8//PCll17KLSeddNLUqVN37drFvRdffDE3bty4ke3b+vXrmUZjxoyx/5wC2FaLABMa8yhj6f/6r//auUuXLVs2E8Z4Wvyv//qv5557jqczj2k2tG/f/vDhI8cff3zDPRUVTz31FCZRj+solmJsR5177rl33XUX+1M6ihZZLdhsf/nEQHBNpaNYwAcPHZo1a5Zlff3rX6e77L8/mopVc+fOxeWZl8EkbsFt3TZjBvZg1XXXXW9zA6zOv/71r5FIhKdmmVEDOmG5rL2Pf/zjeFXC9nTdunVr0aIFFf7mN79p0bKl/eHmOeecs3fv39neRm9q+NuDDz88snXbttWrV33+85/HqgMHD1LSDd+UKVOIEj58+DBNWEf9+te/5lBuNdAQVzqHAoyIRYGd1gf19faHd8ZXvvKVQ4f+yQ7Dolh78MBBdv2EsSr5PGf2urGjAK3w+I2alGhGdTr11G3bthJ+//33Sf+/V1zBtDz77LNpFOWwPmzUJJZeYOy4knjJJZewfeFeNmSH6utvuukmW3SwZcuWE6MQtvLUFqmspPJo/jGgFmT5/4IZ4WEs2D5G8yueffZZnuv99w+sXLnCxg6rmJn+4bvyyitZYtz+7rvv0nsIHruxRYsWWQ3QaF+x+th7Ecazcy9KaVkMH9WaYan0Vezqo+SkSZN27PgrBwNmNQrEosMn2ESF6NO9TxNWGGiC9fjCCy8QtkSuFMjMJ3z/+993wwdU9cwzzzCvcJg8KT7K0sHaYvjIPfXUU3k0qrJ5AjTH5NmxYweVWwowLT84fHhC9De0zR7KNLr0LMtBu9a0CML4GYTp0zvuuIODOXtzO2W6k0TgjcSdd97JtoWtCmvJjiPspEhHjey1j4F8sn2zgxpZzDmUGL9M1N7m2SYX2KPhg6jKogYGWGEHW3JODFRrURdwcBLiLo41Dd9hq6gYOHAg2sAeyr6oZq+h7Bxs73yAJlAsArdH/3s6bOgsnaXIMiPFosC52V7XAP7XZj9bclaL22KbC3DEdpS9MHHQClcMoBJLgRQ7imMEWezibS/JKZOofelp8uTJSaxCa22LTXmeyHKtEhdg78zY2VcYLAV76AECto11X1PkEewthUX9sNWlCR6B8GOPPcZAuBmFDbEfMH/hC1/wD9+A6PdTCNN79PMFF1yAVcxMs8dZZcPn7EcwsJyxc4l0Gr3h5nODY6qowB7CdkyJO8+TjB2GUWGjJiWZURg5L/qLEJZFE9xiA5HEJIg7dsBY+0tSg81Vm2DDhg3j7EXA9RL1kGJvC12iAwFjH4ANGGPV0hwGWy79GThYG/SGf/hYfcxkO+hTiTPJTyp95YYPm4k2vI2MRKxk8r5KMoLMZODB7dnpH+aMfdpHJaw+exngCiAz1MNaI+yHStLyCTwC5/XY4WOh2TGXnqdD6DdLd+bZksdC7PR/QoxJ9AYBB76O+i3XSGXpibh4R0sfDecnPGCf6M+7GAwYk4ZRJ+B62WiYPlGYeWyK7T0PE5qSTFz/N8Qow5UJxDxzvpVxoqR9it6wnYxEcJGWBUxrxMBWuLWCMfYdE0vhSoHYVWeFganAXDFfCfZVcnZzNErllgjMZmomnTCiy6K15UGYp6CJaKkGaIsbbVo3fK+hogI/YmsPrCFE2v85meEZlKCj/LsKoF1MIoswt3BNpaPME3EjPUzhBqsiEZ7FvAZrLIlVDCvG4wHtxoA9BlXRewQoz5Xm0AnrHNuFsGVuKBeF2ngua/r666+fPXs2O2hOeyTy+Lazufrqq2ku8HE1RC1qIDB8PD7RGTNm4BZ5RsI8OPCY7mMhHtANnx/8Drpic8mgXWzmAIRJ1GCfq5GOx8GquPM87thZSds0NGpSohnl9+xmBrdjs0lCEpMg7tiRbsWALMymFX8NzF5SvEgUbsF3U4P/XsCGadG/ardJDqgF0o6+2mdm/vKEDcKxw0eH40Ysyljw7DajHKn0la2+5cuXUxvW2vCRZenJ+yqJm2J60OEEbB0hw9RvUoTUUdJ5HgdPxxKgWi+ekU+gl5IPn+0+TT4dNGTWMhD0CTpt6UAPsDqsN6weE11/CntWUpIsPS8uYvB00kfDT+HYTGKK+z/8YKsYmN9+WPO2DzKvZMNmntEPC4CavUgUZoP7Qz1ymab24p7hZMJRD2EbQoxhYdiuzSUyEREJFw1wyy23UL/7aH3FihUmRWzNqBwHwTGalU8iVrFWrRgzjHatQrbJLEicPmFmLQ/FLZbFGqMS7kWNnFXAgrdnjGtSKh3FMsBsGvLiUVLpKKB+1gMdxe32fQ0juVUkmtfGo1Gb/3EM1hsrk67z4lFYqCxdq5A9FhZai6QQJsWekTJYy2PSsV/96lc5jtgt9uFZXHuMwPDhXLCBbidMneYWma5ms31UAzZ8FnbQIfgjhG3ixInuWxi4wgkTJrBVcmZzxUsmmudxx87OhXhhXGpyk6z+uDMqWsrDirnjJiQxCSifaOzImjJlConcbriPotnfMCXsQRzswyjDEZkOobctkSVGDcxzHtDNKDYuTCc3NHGJO3w2hewZzTa6K5rvkUpfWS57x8mTJzOL3IBC8r6KO4IoGVFOwIRJtMopyQOir4TBv/oc9AkwyjyIdWwGPoGU5EvPnJX/GcGGz54FR00B18/Mc8zwyzN9bt91ADOAOZ986YlEeDrpI87Pstv0wq37l3FyGDNGzoscxQ4HXAm70WIuur+zxIWxqJjxXCl51llnxYpuAJxUkjKscCaTe4dJoxx0aJEAG2TEEiNJYV9Jo7h422AymZzPpSTKSgqFuRGRcG9XbKL7sYfCe2bZUdyO2aaIYNVm2VEpWkV/0rQ5qQA0hFBZ2EzCAPfLD9TPg9BR/fv3x2UQtvecQLtx39rhQ52oxCXJ8FmKA9to10bEDZ8Vw5f5v1CDC3YvOQJY+dTneWDsAlbFNQkolmhGxZKWSXHHjr2OSQK9jddmaOxQxcxxXxMD6kcpMcY6CXD6lhU7zwGdYyEHHjlAo8OHDFDgzqP/NQ9Lz09fGf4R5ACKMXYAtarIYm9qK4vWbfVZFsJG7zHEDT0V/YKVzeRsfEKipWdfEUBQLWoV+oePFHoGG9gXEmBVWp9bybg0uvREIjyd9OFJJt1tWDQt5kV/gdA+BjCsKqYgg+olRVm2bBljzGQlbG0xQTkkseNjT2cpfqLVpGEStWGJ1W/YF8zcZtnBPDMfwczGJPsqoLWFjrKqyWWSxbYetagBL54OsR1l2Pf1TTKt5sw6Crx4OiAqgwYNCpw/WM84CFu3rlr8r+36rfDzzz/PQYRTAuf1wKbYSNekRofPVYgY2NTyD5/tweklLO/Xrx8u3lICuErSItHYudrimmRZyWdUNsQdO7CUIUOGYJWdhzDJXqRbn0ybNo3HYRVw+z333BPX9RtePAUaHT50l6i9ujRQ93T7KmpUJn0YGMGGtzWRiH32YRUyk+3tOlmB1cfe0U0q22f7iVrUgBdPmUTDx7gwl6xCu3JwtOGz1pljmMd6ZOnxXKQEyMAYERdPJ33EOWWmCzsgzj0E/GM8atQoliuriDD7XJupOFZ09MF4vyYcFmxRmW3OBVx11VWk2A7LzXX8PkvXzFixYoVbHrkm0FEuMGHCBOxBJl0KXibXHQXWFp4CwwLnQvsbFf9GGxFlk+5OmTki7vDZKzKnf5MmTcL32UdNy5cvTz58GG/2Z0ns2IELp2VSKFjTccfOwKsyhfhnYXqV/RZhuzG2T2JTMiDJ8AFN2DmP6f3tb38bt8Ckwu8XavXZ5x1mHmduJry9VuFMmXz1UYOrJDPs9kTDhxDiPOkctjv0Ev2JqTZ8Is94Oukjc8m0UcdNMNXsg2XHY9H/JhSjzq7N3mYwNVEsli5hrl65o0RnYAgrFvpH/xunbmNrn168HIUdJWKJO2MT594FscWjgCvvCNEkqyduRxmcBthvEnAt5qGjwKqiT+gBZ5gl3nDDDRjgX8ysWzoWz+LFjxK1qAEvnh1xh4/jLCm4DPZheFi6se/R7/vEHT7PoDBMskrijl1aJkFYJhlWVWDscK9sv/D1THV8sfP7jB3RKcf+9AyYSeDFsybR8NEE3n9A9LcDmVdAAGUiPdd9ZfXEHUE2qTZ2XDHjjDPOsPS4q89MAi+eHVZPYPiAMwanC3yU9RJMnjyZwvkZPhGLp5M+sjplsg9CF1mlhN988805c+bYF4jslztYsWw5Z8yY4Xad86I/QWk/kZojUGtMatu27YsvvshaZTG4LyD0i/5UMTs4/6cy26J/+BW7aMMlUUcZ7G1te+vIQ0eBdQLPTg9wTkIm3cd+uBhWqX81suOhWPKfGcueRMNHB7Ilb9OmTe/evfEp+Ry+RGNXQJMgduwA85jhzBw2hcx2e1tuJSmWh0+zkqy+QYMGYRUbC1afcwj2uV3+V5+9rAYMmzhxIrb53wPnYfXFDp8tva8e/S/bDBs27M4773QdlZ/hE7F4OukjK8ns3r07Y2nvNwiA/bFU7Ot+e1+PN2EhWUruYE2yQswkPJr7KmBcmJT2/YicEttRV111lVuiseSno3AfSCNOzUwCzgGxY2ew/7355pvtTXtOKbbhS3fs8jOjYseOEx5WJfq+DGMX+9IiF6Q4fNaBxbb6LDEPqy92+D4X/S+okO6VOIqZlLfhEwE8nfTR8D7QG7T06dy58zvvvMPADx48mFn46U9/2suI4n48wn6BIp9s2rTp97///f/5P/+nSExK3lGAYfnvpfXr148YMeJjH/vY+PHj2Wv37NnTy4hifZV/q6Cohq84J3kqYwcaPkhl9XHNp1XFPHzCTyT6A6J+spJMhjYwqLEpBacYTCqJjgINXywau2woBqtKYgSLc/hEyJIJjLQFNN7JKdqOOnDgwHHHHafhS4LGrtQpzhHU8BU/4UumEEIIUZbESqb3exZCCCGESI4kUwghhEgJSaYQQgiREvosMxxiX3kLIYQoM3TKFEIIIVJCkimEEEKkQEXF/wcCr2Fto483PAAAAABJRU5ErkJggg==\n", "text/plain": ["<IPython.core.display.Image object>"]}, "execution_count": 9, "metadata": {"image/png": {"width": 400}}, "output_type": "execute_result"}], "source": ["NbImage(\"images/backtest.png\", width=400)"]}, {"cell_type": "markdown", "metadata": {"collapsed": true}, "source": ["Comparaison de plusieurs jeux de param\u00e8tres (source [Backtesting a Simple Stock Trading Strategy](https://www.r-bloggers.com/backtesting-a-simple-stock-trading-strategy/))"]}, {"cell_type": "code", "execution_count": 9, "metadata": {"slideshow": {"slide_type": "fragment"}}, "outputs": [{"data": {"image/png": "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\n", "text/plain": ["<IPython.core.display.Image object>"]}, "execution_count": 10, "metadata": {"image/png": {"width": 500}}, "output_type": "execute_result"}], "source": ["NbImage(\"images/backtest2.png\", width=500)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Tests exhaustifs\n", "\n", "* Tester de nombreux jeux de param\u00e8tres\n", "* Tester sur un grand nombre de s\u00e9ries financi\u00e8res\n", "* Tester la r\u00e9sistance aux crises\n", "* Prise en compte de d\u00e9faut de simulation : co\u00fbt de transaction, slippage"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Portefeuille de strat\u00e9gies\n", "\n", "* Impl\u00e9menter une seule strat\u00e9gie est risqu\u00e9.\n", "* Construction de portefeuilles de strat\u00e9gies (plus d'une centaine)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Importance de l'informatique\n", "\n", "* Puissance de calcul\n", "* Agilit\u00e9\n", "* Passage en production\n", "* R\u00e9sistance aux pannes\n", "* Utilisation de [stop-order](http://www.investopedia.com/university/intro-to-order-types/stop-orders.asp)"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Trading daily, intraday\n", "\n", "* Daily : calcul des d\u00e9cisions chaque jour\n", "* Intraday : calcul des d\u00e9cisions chaque minute\n", "* Haute Fr\u00e9quence : calcul d'une d\u00e9cision en quelques millisecondes\n", "\n", "Plus la vitesse de trading est importante, plus l'informatique joue un grand r\u00f4le, plus le boulot est technique.\n", "\n", "* La course aux millisecondes : [Hibernia Network](https://en.wikipedia.org/wiki/Hibernia_Networks)."]}, {"cell_type": "markdown", "metadata": {}, "source": ["## R\u00e9flexions sur la finance\n", "\n", "* Machine learning, exploitation des news, signaux autres que financiers\n", "* C\u00f4t\u00e9 \u00e9thique\n", "* Parall\u00e8le avec le real-time-bidding"]}, {"cell_type": "markdown", "metadata": {"collapsed": true}, "source": ["### Pourquoi le machine learning ?\n", "\n", "* **Back test** : m\u00e9thode issue du machine learning\n", "* **Bo\u00eete noire** : une fa\u00e7on d'utiliser l'information qu'on ne sait pas utiliser de mani\u00e8re \u00e9vidente\n", "* **Traitement des news** : celle-ci ont une influence non n\u00e9gligeable sur les cours mais ce n'est pas une informatique num\u00e9rique.\n", "* **Deep learning** : le deep learning fonctionne sur des images, du son, du texte, pourquoi pas sur des cours financiers."]}, {"cell_type": "markdown", "metadata": {"collapsed": true}, "source": ["### Ethique\n", "\n", "* Trading haute fr\u00e9quence : quelques millisecondes d'avance sur les concurrents\n", "* plus de 50% des \u00e9changes issus du trading haute fr\u00e9quence\n", "* Une plus grande fluidit\u00e9 (possibilit\u00e9 d'acheter et de vendre \u00e0 tout moment)\n", "* Quelle utilit\u00e9 \u00e9conomique ?\n", "* Recrutement des meilleurs talents"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Un parall\u00e8le avec Bitcoin\n", "\n", "* Le principe de [Bitcoin](https://fr.wikipedia.org/wiki/Bitcoin) : miner\n", "* La course \u00e0 la puissance"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Un parall\u00e8le avec le Real Time Bidding\n", "\n", "* [Real Time Bidding](https://fr.wikipedia.org/wiki/Real_Time_Bidding), plate-formes d'\u00e9changes, ench\u00e8res\n", "* Publicit\u00e9 sur Internet\n", "* Un champion national : Criteo\n", "* M\u00e9canisme des ench\u00e8res\n", "* Diff\u00e9rence avec la finance : utilisation des donn\u00e9es"]}, {"cell_type": "markdown", "metadata": {}, "source": ["### Ing\u00e9ni\u00e9risation de la finance\n", "\n", "* Popularisation du trading automatique.\n", "* La finance n'est plus aussi attractive.\n", "* Des traders qui passent de la finance \u00e0 la data science."]}, {"cell_type": "markdown", "metadata": {"collapsed": true}, "source": ["## Conclusion\n", "\n", "* Le r\u00f4le pr\u00e9pond\u00e9rant de l'informatique\n", "* L'ex\u00e9cution n'est plus manuelle, trop rapide, en trop grand nombre\n", "* Le savoir est converti sous forme d'algorithmes.\n", "* La finance en dehors de la finance : [Chine: la finance de l'ombre atteint un record](http://lexpansion.lexpress.fr/actualites/1/actualite-economique/chine-la-finance-de-l-ombre-atteint-un-record_1899027.html)"]}, {"cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": []}], "metadata": {"kernelspec": {"display_name": "Python 3", "language": "python", "name": "python3"}, "language_info": {"codemirror_mode": {"name": "ipython", "version": 3}, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.5"}}, "nbformat": 4, "nbformat_minor": 2}